Kernel power k-means (KPKM) leverages a family of means to mitigate local minima issues in kernel k-means. However, KPKM faces two key limitations: (1) the computational burden of the full kernel matrix restricts its use on extensive data, and (2) the lack of authentic centroid-sample assignment learning reduces its noise robustness. To overcome these challenges, we propose RFF-KPKM, introducing the first approximation theory for applying random Fourier features (RFF) to KPKM. RFF-KPKM employs RFF to generate efficient, low dimensional feature maps, bypassing the need for the whole kernel matrix. Crucially, we are the first to establish strong theoretical guarantees for this combination: (1) an excess risk bound of O( k^3/n), (2) strong consistency with membership values, and (3) a (1 + ε) relative error bound achievable using the RFF of dimension poly(ε^{−1} logk). Furthermore, to improve robustness and the ability to learn multiple kernels, we propose IP-RFF-MKPKM, an improved possibilistic RFF-based multiple kernel power k-means. IP-RFF-MKPKM ensures the scalability of MKPKM via RFF and refines cluster assignments by combining the merits of the possibilistic and fuzzy membership. Experiments on large-scale datasets demonstrate the superior efficiency and clustering accuracy of the proposed methods compared to the state-of-the-art alternatives.

In multimodal sentiment analysis, modality missingness and quality degradation are common. Existing methods often rely on batch-level modality generation, generation but neglect sample-level missingness, hence their flexibility is limited severely in real-world scenarios. To address this, Sample-specific Modality Diagnosis and Cross-modal Enhancement for Incomplete Multimodal Representations (SMCIR) is proposed. Specifically, The Dynamic Multi-feature Fusion Detector (DMFD) is presented, which detects missingness and severity at the sample-level using indicators such as information entropy, modality similarity, and mutual information. Unlike batch-based methods, the DMFD provides fine-grained detection and adaptive responses, improving sensitivity to modality disturbances. Meanwhile, the Context-aware Modality Completion Generator (CMCG) is developed to restore missing modalities through context-guided reconstruction using multiscale feature fusion and cross-modal attention. In this way, the proposed CMCG method can avoid redundancy and inconsistency, enhancing the consistency and discriminativity of the fused representation. In CMCG, the text modality serves as a stable guide to improve context consistency. Experiments on the CMU-MOSI and CMU-MOSEI datasets show that SMCIR outperforms existing full-modal and non-recovery-based methods, well validating its efficacy and superiority in multimodal learning.

Multi-view graph clustering (MVGC) for remote sensing data has gained increasing attention due to its ability to integrate complementary information across modalities while capturing spatial dependencies in heterogeneous data. Although current methods based on graph contrastive learning achieve strong performance, they often misidentify intra-cluster samples as negatives, leading to class conflicts and reduced clustering accuracy. Graph masked autoencoders have recently shown promising potential in learning robust representations through masked reconstruction, but their application to remote sensing data remains underexplored. This challenge is especially notable in the multi-view remote sensing setting, where high heterogeneity and complex spatial structures increase the difficulty of effective representation learning. To address these issues, we propose Clustering-Guided graph Mask AutoEncoder (CG-MAE), the first framework to extend graph masked autoencoders to multi-view remote sensing clustering. We introduce a clustering-guided masking strategy that selectively masks nodes near cluster centers and intra-cluster edges, which are crucial for capturing key structural information. By reconstructing these masked components, the model is encouraged to focus on learning features that are highly relevant to clustering. To further improve training stability and efficiency, we design an easy-to-hard node masking strategy that enables the model to gradually learn from increasingly challenging patterns. Additionally, we propose a dual self-adaptive learning mechanism that encourages the model to align more closely with the underlying semantic distributions. Extensive experiments on four widely used multi-view remote sensing datasets demonstrate that CG-MAE consistently outperforms state-of-the-art methods in both clustering accuracy and representation quality.

Brain network analysis technology reveals the organizational mechanism and information processing mode by constructing the structural connection network between brain regions. It has achieved satisfactory results in brain disease prediction tasks, promoting the progress of neuroscience. In recent years, graph transformer has become the most mainstream method for brain analysis with its powerful feature extraction ability and attention mechanism. However, these methods face two challenges, i.e., lack of interpretability, and neglect of semantic associations among brain regions. To solve these problems, we proposed a large language model (LLM)-driven causal knowledge brain network transformer framework, termed BrainCKT, which is plug-and-play, and can adapt to most of the existing mainstream graph transformer-based methods. Specifically, we constructed a brain region causal graph and used its adjacency matrix to guide the learning process of the self-attention mechanism. In addition, we constructed a brain science knowledge graph and encoded it through a pre-trained model to enhance the original brain region features. Finally, we integrated BrainCKT into four mainstream graph transformer baselines for verification. Experimental results on two brain imaging datasets proved the effectiveness of BrainCKT.

Large Vision-Language Models (LVLMs) enhance the capabilities of Large Language Models by integrating visual inputs, thereby enabling advanced multimodal reasoning across diverse applications. However, these enhanced reasoning capabilities introduce new security risks, particularly to jailbreaking attacks that bypass built-in safety mechanisms to elicit harmful or unauthorized outputs. While recent efforts have explored adversarial and typographic prompts, most existing attacks suffer from three key limitations: reliance on auxiliary models, limited effectiveness in black-box scenarios, and inadequate exploitation of the LVLMs' intrinsic reasoning abilities. In this work, we propose TVChain, a novel black-box jailbreaking framework that explicitly intervenes in both the visual and textual reasoning processes of LVLMs. TVChain decomposes malicious prompts into a sequence of semantically meaningful sub-images that represent relevant objects and behaviors, thereby circumventing direct exposure of illicit content. In parallel, a carefully designed chain-of-thought (CoT) textual prompt is employed to steer the model's reasoning toward reconstructing the intended activity in a covert yet effective manner. We demonstrate that this compositional prompting strategy reduces the likelihood of triggering safety mechanisms while preserving attack efficacy. Extensive evaluations on eleven LVLMs (seven open-source and four commercial) across two benchmark datasets and three state-of-the-art defenses validate the effectiveness and robustness of TVChain.

Clustering is a fundamental task in unsupervised learning, but most existing methods heavily rely on hyperparameters such as the number of clusters or other sensitive settings, limiting their applicability in real-world scenarios. To address this long-standing challenge, we propose a novel and fully parameter-free clustering framework via Self-supervised Consensus Maximization, named SCMax. Our framework performs hierarchical agglomerative clustering and cluster evaluation in a single, integrated process. At each step of agglomeration, it creates a new, structure-aware data representation through a self-supervised learning task guided by the current clustering structure. We then introduce a nearest neighbor consensus score, which measures the agreement between the nearest neighbor-based merge decisions suggested by the original representation and the self-supervised one. The moment at which consensus maximization occurs can serve as a criterion for determining the optimal number of clusters. Extensive experiments on multiple datasets demonstrate that the proposed framework outperforms existing clustering approaches designed for scenarios with an unknown number of clusters.

Multi-view clustering aims to uncover shared semantics and complementary information across different views. However, the inherent heterogeneity among views poses significant challenges to effective collaborative modeling and information integration. While recent studies have introduced distillation-based mechanisms to enhance cross-view consistency and alleviate heterogeneity, these approaches often rely on manually defined knowledge transfer paths or fixed fusion weights, which are inflexible in handling complex and dynamic view relationships in practice. To address this issue, we propose HOARD: a novel framework for Hierarchical crOss-view Alignment for multi-view clusteRing via Decoupled information distillation. HOARD structurally decouples multi-view representations into shared and specific components, and performs hierarchical alignment. Specifically, we introduce a granular-ball contrastive alignment to enhance the semantic consistency of shared features, and a prototype collaborative transmission alignment strategy to align specific features while preserving view-specific structural characteristics. Moreover, we design an information distillation unit to adaptively model cross-view knowledge transfer in both feature spaces. An attention mechanism is further employed to integrate shared and specific information. Extensive experiments on benchmark datasets demonstrate that HOARD significantly improves alignment quality and clustering performance, achieving state-of-the-art results.

Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However, on large-scale real-world graphs, GNNs face two major challenges: (1) GNNs struggle to ensure scalability and efficiency as repeated aggregation of large neighborhoods incurs significant computational overhead; (2) GNNs suffer from over-smoothing, where excessive propagation makes node representations indistinguishable, hindering model expressiveness. To tackle these, we propose ScaleGNN, which adaptively fuses multi-hop node features for scalable and effective graph learning. We first compute per-hop pure-neighbor matrices to isolate exclusive structural signals, then apply lightweight fusion to balance low- and high-order information, preserving both local detail and global correlations. To curb redundancy and over-smoothing, we introduce Local Contribution Score (LCS)–based masking to prune low-relevance high-order neighbors, and impose learnable sparsity to selectively integrate valuable multi-hop features. Extensive experiments on real-world datasets show that ScaleGNN consistently outperforms state-of-the-art GNNs in both predictive accuracy and computational efficiency. The source code is available at https://github.com/lx970414/ScaleGNN.

Out-of-Distribution (OOD) detection, which seeks to identify samples deviating from the In-Distribution (ID) training distribution at test time, is crucial for building robust machine learning systems. While extensive efforts have been made for Euclidean data, OOD detection on graph-structured data remains relatively underexplored. On the one hand, the specific properties of a graph may be attributed to its substructures. On the other hand, acquiring labeled data for graph learning is typically time-consuming and labor-intensive. Toward this end, in this paper, we propose a novel kernel-enhanced graph substructure learning framework termed KEGOD for unsupervised graph OOD detection. Specifically, we introduce a learnable graph generator to construct the augmented graph view that preserves distinguishable structure information. Then, for both the input graph and augmented view, a graph neural network (GNN) branch and a graph kernel (GK) branch are incorporated to explore graph latent patterns. By performing multi-branch concordance learning on the extracted graph patterns, our KEGOD captures complementary ID structural semantics in both implicit and explicit manners, enabling reliable detection of OOD graphs through semantic inconsistency. Finally, we build a self-adaptive training mechanism to automatically control diverse sensitivities of the graph patterns. Experimental results on several public graph datasets reveal the superiority of our KEGOD. Our code is available at~ https://github.com/jamesyifan/KEGOD.

Out-of-distribution (OOD) detection serves as an unknown-handling mechanism for open-world classification, enabling the identification of OOD data that diverge semantically from in-distribution (ID) data. The learning strategy known as outlier exposure (OE) enhances this process by incorporating OOD data during model training, directly making models learn to discern between ID and OOD patterns. However, in practice, the collected OOD data often contain many ID semantics, of which the scenario is commonly referred to as wild OOD detection. It can markedly compromise the reliability of models in OOD detection, yet few studies have addressed this critical issue. In this paper, we theoretically analyze wild OOD detection from the instance and distribution facets, respectively, to better comprehend its challenges and accordingly introduce two general solutions. At the instance facet, ID/OOD indicators contain errors due to the wild nature, where some data are of OOD labels yet should be assigned as ID. Hence, we introduce a general framework that can dynamically estimate the true ID/OOD indicators solely based on wild OOD data, thereby mitigating their negative impacts. At the distribution facet, the wild OOD distribution is a mixture of ID and OOD distributions, where the ID sub-distribution can mislead the model. We therefore propose a resampling scheme to remove the potential ID sub-distribution, with resampling probabilities estimated from the known ID distribution, enabling OE training to better address wild OOD detection. We provide theoretical guarantees for both solutions and develop algorithms that enhance their practical efficacy, ultimately integrating them into a unified framework that leverages their complementary strengths. Ultimately, we validate our approaches through comprehensive empirical evaluations across a range of wild OOD detection scenarios, clearly demonstrating the superior performance and reliability of our methods when compared to advanced counterparts.

Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, and network security. Significant strides have been made in leveraging Graph Neural Networks (GNNs) to achieve remarkable success in these areas. However, in real-world scenarios, the training environment for models is often far from ideal, leading to substantial performance degradation of GNN models due to various unfavorable factors, including imbalance in data distribution, the presence of noise in erroneous data, privacy protection of sensitive information, and generalization capability for out-of-distribution (OOD) scenarios. To tackle these issues, substantial efforts have been devoted to improving the performance of GNN models in practical real-world scenarios, as well as enhancing their reliability and robustness. In this paper, we present a comprehensive survey that systematically reviews existing GNN models, focusing on solutions to the four mentioned real-world challenges including imbalance, noise, privacy, and OOD in practical scenarios that many existing reviews have not considered. Specifically, we first highlight the four key challenges faced by existing GNNs, paving the way for our exploration of real-world GNN models. Subsequently, we provide detailed discussions on these four aspects, dissecting how these solutions contribute to enhancing the reliability and robustness of GNN models. Last but not least, we outline promising directions and offer future perspectives in the field.

Deep neural networks possess remarkable learning capabilities but are vulnerable to overfitting in the presence of mislabeled data. A well-known memorization effect causes networks to first fit clean samples and later memorize noisy labels. Although early stopping can partially alleviate this issue, it cannot prevent the accumulation of incorrect knowledge or recover information lost due to mislabeled inputs. In this paper, we introduce an innovative mechanism for continuous review and timely correction of learned knowledge. Our approach allows the network to repeatedly revisit and reinforce correct information while promptly addressing any inaccuracies stemming from mislabeled data. We present a novel method called self-not-true-distillation (SNTD). This technique employs self-distillation, where the network from previous training iterations acts as a teacher, guiding the current network to review and solidify its understanding of accurate labels. Crucially, SNTD masks the true class label in the logits during this process, concentrating on the non-true classes to correct any erroneous knowledge that may have been acquired. We also recognize that different data classes follow distinct learning trajectories. A single teacher network might struggle to effectively guide the learning of all classes at once, which necessitates selecting different teacher networks for each specific class. Additionally, the influence of the teacher network's guidance varies throughout the training process. To address these challenges, we propose SNTD+, which integrates a class-wise distillation strategy along with a dynamic weight adjustment mechanism. Together, these enhancements significantly bolster SNTD's robustness in tackling complex scenarios characterized by label noise.

Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC potentially does not fully leverage the multi-view information, due to the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, an analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches both on eight benchmark MvC datasets and two spatially resolved transcriptomics datasets.

Temporal graph learning focuses on graph deep learning in real-world dynamic scenarios, which uses interaction sequence instead of adjacency matrix to observe the graph dynamic changes more microscopically from the perspective of time evolution. However, current temporal graph methods only focus on extra dynamic information, ignoring the large amount of multi-modal information contained in the real world. These information can reflect the rich changes in the real world from different perspectives. Ignoring them means that temporal graph learning still lacks the ability to restore and mine more complex real-world data. We argue that the main challenges causing the above phenomenon in temporal graph learning are the lack of multi-modal architecture and public multi-modal datasets. To solve the above challenges, we propose ModalTGL, which enhances the computational efficiency of the model in complex dynamic scenarios by introducing the dictionary graph network, and achieves multi-modal fusion by embedding tuning. In addition, we also discuss the effects of different time encoding functions on dynamic information preservation. At the data level, we build several multi-modal temporal graph datasets from different areas, and compare with multiple SOTA methods on these datasets. The experimental results verify the effectiveness of the ModalTGL method, achieving the performance improvement of up to 18.48%.

Multi-view clustering (MVC), as an important machine learning task, aims to group data into distinct groups by leveraging complementary and consistent information across multiple views. During the last two decades, it has been widely studied, and many methods have been proposed, which has brought incredible development to this field. However, few works comprehensively summarize existing methods and point out the potential challenges in this field for the next decades. To this end, our survey thoroughly reviews existing MVC methods according to three taxonomies, i.e., techniques, fusion strategies, and scenarios. Specifically, seven typical techniques, four fusion strategies, and five typical scenarios are included. Besides, we also collect the commonly used datasets and analyze the performance of typical MVC methods. Moreover, we summarize six application scenarios of existing MVC methods ranging from computer vision, and information retrieval tasks to medical diagnosis and bio-informatics. In particular, we point out seven interesting future directions in this field, which will definitely enlighten the readers.

Federated multi-view clustering is an emerging machine learning paradigm that groups the data with each view distributed on an isolated client while preserving their privacies. Although recent researches have proposed a few feasible solutions, they are severely limited by two drawbacks. In specific, the clients are required to share their data representations at each iteration of model training, leading to heavy communication overhead. On the other hand, existing researches handle large-scale data by employing the matrix factorization and neural network encoding techniques, failing to utilize their similarity information sufficiently. To address these issues, we propose a communication-efficient federated multi-view clustering framework by approximating the data representation with pseudo-label and centroid matrix, where the latter two are shared in model training. Meanwhile, the framework is instanced by incorporating linear kernel function to consider the data pairwise similarities. Note that, corresponding linear kernels are not required to compute explicitly, making the resultant method able to be optimized in linear complexity to the number of samples. Nevertheless, the proposed method is evaluated on benchmark datasets. It not only achieves inspiring results (26.84% accuracy improvement on average, 2.9$_\times$×-2153$_\times$× computation speedup and 98.4% communication overhead reduction at most) compared with existing federated multi-view clustering methods, but also outperforms centralized multi-view clustering approaches on performance and computation efficiency.

With the accumulation of resources in the era of Big Data and the rise of pre-trained models in deep learning, optimizing neural networks for various tasks often involves different strategies for fine-tuning pre-trained models versus training from scratch. However, existing optimizers primarily focus on reducing the loss function by updating model parameters, without fully addressing the unique demands of these two major paradigms. In this paper, we propose DualOpt, a novel approach that decouples optimization techniques specifically tailored for these distinct training scenarios. For training from scratch, we introduce real-time layer-wise weight decay, designed to enhance both convergence and generalization by aligning with the characteristics of weight updates and network architecture. For more importantly fine-tuning, we integrate weight rollback with the optimizer, incorporating a rollback term into each weight update step. This ensures consistency in the weight distribution between upstream and downstream models, effectively mitigating knowledge forgetting and improving fine-tuning performance. Additionally, we extend the layer-wise weight decay to dynamically adjust the rollback levels across layers, adapting to the varying demands of different downstream tasks. Extensive experiments across diverse tasks, including image classification, object detection, semantic segmentation, and instance segmentation, demonstrate the broad applicability and state-of-the-art performance of DualOpt.

Communication-efficient distributed learning has achieved remarkable progress in training large-scale deep neural networks across numerous clients. However, in heterogeneous environments-where local data distributions vary significantly-the empirical performance of many such algorithms degrades sharply. Moreover, existing theoretical analyses often depend on overly restrictive assumptions, such as bounded data heterogeneity, which may not be valid even for a single client. In this work, we introduce a general gradient normalization strategy that can be seamlessly integrated into a wide range of distributed learning algorithms, including compressed distributed stochastic gradient descent, federated averaging, and asynchronous variants. Our theoretical analysis demonstrates that this normalization technique effectively mitigates the negative impact of data heterogeneity, allowing these algorithms to achieve linear speedup rates with only requiring the boundedness of initialization data heterogeneity. Extensive numerical experiments further confirm the practical effectiveness and theoretical guarantees of our approach.

Subspace clustering is one of the most popular clustering methods due to its effectiveness. Although subspace clustering methods have been demonstrated to achieve promising performance, they still lack interpretability, especially when handling high-dimensional complicated data. To bridge this gap, this paper focuses on the interpretability of subspace clustering and proposes a novel interpretable subspace clustering method. Our goal is to answer two key questions about the interpretability in subspace clustering: 1) when handling an individual sample, which features should work for this sample? 2) Which cluster or subspace will the features that work put this sample into? To answer these two questions, we design two new interpretability regularized terms and plug them into the subspace clustering. In this way, we show that interpretability can be used to improve the clustering performance in turn. Extensive experiments on benchmark data sets demonstrate the effectiveness of our method in terms of clustering performance and interpretability.

Spatial transcriptomics has revolutionized the ability to investigate transcriptional patterns within tissue morphology. However, many ST clustering pipelines operate on a single preselected gene set, typically prioritizing either highly variable genes (HVGs) or spatially variable genes (SVGs), and therefore may not directly model how genes with different levels of global variability provide complementary cues for spatial domain identification. Although non-HVG signals can be partially captured through SVG selection and spatial graph modeling, a dedicated two-view formulation that disentangles high-variance and low-variance gene subsets and fuses them under a unified objective remains underexplored. To this end, we propose a Spatial Transcriptomics clustering framework for Cross-view information Fusion, termed STCF, which casts HVGs and low-variability genes (LVGs) as two gene-expression views and integrates them via a plug-and-play cross-view fusion strategy. Specifically, STCF introduces a cross-view fusion mechanism that employs reverse-scaled cosine error loss (R-SCE) to balance alignment and separation of gene embeddings, ensuring robust representation learning while preserving spatial coherence, which enhances the model's ability to resolve fine-grained spatial structures. Extensive experiments on three benchmark datasets (DLPFC, HBC, and MBA) demonstrate the superiority, effectiveness, and transferability of STCF. Case studies further validate its ability to uncover latent spatial patterns and improve clustering precision.

Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view fusion, which hampers the quality of the shared latent space and leads to suboptimal clustering performance. To address this issue, we propose the Generalized Multi-view Auto-Encoder (GMAE), a framework designed to preserve cross-view complementarity through disentangled representation learning. Specifically, GMAE employs dual-path autoencoders to decouple source features into view-specific and view-common embeddings, facilitating the discovery of clearer clustering structures. We further construct cross-view adversarial discriminators to guide view-specific encoders in capturing more discriminative features. By strategically modulating mutual information, GMAE effectively aligns distributions and prevents representation collapse, ensuring the generation of robust, non-trivial embeddings. Comprehensive experiments on 13 benchmark datasets demonstrate that GMAE consistently outperforms state-of-the-art methods in both complete and incomplete MVC tasks.

Single-cell multi-view clustering enables the exploration of cellular heterogeneity within the same cell from different views. Despite the development of several multi-view clustering methods, two primary challenges persist. First, most existing methods treat the information from both single-cell RNA (scRNA) and single-cell Assay of Transposase Accessible Chromatin (scATAC) views as equally significant, overlooking the substantial disparity in data richness between the two views. This oversight frequently leads to a degradation in overall performance. Additionally, the majority of clustering methods necessitate manual specification of the number of clusters by users. However, for biologists dealing with cell data, precisely determining the number of distinct cell types poses a formidable challenge. To this end, we introduce scUNC, an innovative multi-view clustering approach tailored for single-cell data, which seamlessly integrates information from different views without the need for a predefined number of clusters. The scUNC method comprises several steps: initially, it employs a cross-view fusion network to create an effective embedding, which is then utilized to generate initial clusters via community detection. Subsequently, the clusters are automatically merged and optimized until no further clusters can be merged. We conducted a comprehensive evaluation of scUNC using six distinct single-cell datasets. The results underscored that scUNC outperforms the other baseline methods.

Deep contrastive multi-view clustering has attracted considerable attention for its ability to extract shared representations across heterogeneous views. Despite its effectiveness, existing approaches usually assume full cross-view alignment, an assumption often violated in practice due to sensor noise, transmission loss, or inconsistent data augmentation. This partial view alignment substantially degrades performance, while current solutions relying on fixed pair selection or uniform weighting fail to resolve the semantic ambiguity of unaligned samples. Consequently, latent cross-view semantic relationships remain underutilized, while erroneous positive pairs unduly dominate the contrastive objective, compromising robustness under low alignment rates or noisy conditions. To address these challenges, we propose Dynamic Weight-Enhanced InfoNCE (DW-InfoNCE), a contrastive learning framework designed for partially view-aligned clustering. The framework introduces a cross-view positive pair mining strategy that iteratively identifies reliable pairs from unaligned samples through quantile-adaptive thresholds and uniqueness constraints, enabling recovery of latent semantic structures obscured by incomplete alignment. In addition, an adaptive faulty pair suppression mechanism is developed to identify semantically inconsistent pairs via temporal loss smoothing and global statistics, while attenuating their impact with Gaussian-based adaptive weights. Extensive experiments on five benchmarks demonstrate DW-InfoNCE consistently outperforms state-of-the-art methods across alignment rates, with significant gains under severe misalignment. The code of DW-InfoNCE can be publicly downloaded at https://github.com/qiuyu99627/ DWInfoNCE.git.

Single-domain generalized object detection aims to enhance a model’s generalization to multiple unseen target domains using only data from a single source domain during training. This is a practical yet challenging scenario, as it requires the model to address domain shift without incorporating target domain data into the training process. In this paper, we propose a novel phrase-grounding-based style transfer (PGST) approach for the task. Specifically, we first define textual prompts to describe objects for potential unseen target domains. Then, we leverage the grounded language-image pre-training (GLIP) model to capture the styles of these target domains and perform style transfer from the source to the target domains. The style-transferred visual features from the source domain are semantically rich and closely approximate those of their hypothetical counterparts in the target domain. Finally, we employ these style-transferred visual features to fine-tune GLIP. By introducing these imaginary counterparts, the detector can be effectively generalized to unseen target domains using only a single source domain during training. Our method significantly improves mean average precision (mAP), with an average increase of 8.8% across five diverse weather-driving benchmarks. Notably, our approach outperforms or matches the performance of domain-adaptive object detection methods, which require target domain data for training, in several challenging scenarios.

Multi-view clustering (MVC) has emerged as a powerful tool for analyzing complex datasets by leveraging consistent and complementary information from multiple sources. However, MVC faces three critical challenges in real-world scenarios: (1) Sample-level misalignment due to unknown cross-view correspondence, which introduces noisy correlations, (2) Feature-level heterogeneity from divergent dimensional spaces across views obscuring shared discriminative patterns, and (3) Dynamic-view inefficiency when integrating sequentially arriving data under privacy or sensor constraints. These challenges collectively hinder the clustering performance of existing studies, thus giving rise to a unified framework. To bridge this gap, we propose ASIA-MVC, an anchor-guided sample-and-feature incremental alignment framework for MVC, which is the first attempt in incremental learning on sample-unpaired multi-view data. First, the sample alignment module dynamically maps unpaired samples across views via anchor-based bipartite graphs. Second, the feature-aligned module employs an orthogonal decomposition strategy to unify heterogeneous feature spaces while preserving discriminative structures. Third, the novel incremental fusion framework integrates the dual-aligned modules under the guidance of shared anchors, enabling efficient cross-view representation learning. Furthermore, to solve the resulting problem, we develop a novel three-step alternate optimization algorithm with guaranteed convergence. Finally, the proposed method is validated in extensive experiments and achieves leading cluster efficiency and an outstanding sample-aligned effect.

The anchor-based multi-view clustering method has recently attracted considerable attention due to its superior efficiency. However, most existing methods construct a consensus anchor graph based solely on view-level contributions, overlooking the varying importance of individual samples across different views. Moreover, these methods fail to ensure that anchors are evenly distributed across clusters. Thus, we propose a novel and scalable multi-view clustering method, called Sample-Level Weighted and Structure-Enhanced Anchor Graph Learning for Scalable Multi-View Clustering (SLWSE-AGL). Specifically, we introduce a sample-level weighting mechanism based on anchor self-representation learning, enabling the constructed consensus anchor graph to capture the varying importance of samples in different views. Additionally, we incorporate a structure-enhancement constraint to encourage the learned anchors to be more evenly distributed among clusters, leading to more balanced and meaningful cluster partitions. Furthermore, we employ an anchor-to-sample label propagation mechanism that directly yields the final clustering results, thereby avoiding the information loss associated with the two-stage clustering processes. Extensive experiments demonstrate the superior performance of our method compared to state-of-the-art multi-view clustering approaches. The code of SLWSE-AGL is publicly available at https://github.com/tangchuan2000/SLWSE-AGL.

Multi-view clustering (MVC) aims to uncover the consistent structure and latent distribution of data by integrating information from diverse perspectives. A series of MVC models have been developed, but most of them are limited. They either naively fuse multi-view data into a single view or process each view in isolation, thereby neglecting the complex relationships between views. Among which, multi-stage approaches are heavily dependent on pre-learning and post-processing steps. To overcome these limitations, a one-stage MVC model, namely the embedded multi-view clustering approach with tensor self-representation and adaptive graph learning (EMCTGL), is proposed. In the proposed model, a step-structured data tensor is constructed and then decomposed to learn a cross-view self-representation tensor, effectively capturing the global topological relationships across all views. To achieve a clearer global subspace structure, a novel TLog-induced non-convex low-rank regularization is imposed on the rotated representation tensor. Under relaxed symmetry constraints, the self-representative tensor guides the learning of view-specific affinity graphs and a σ-norm penalty is applied to promote approximation of symmetry of affinity graphs. Subsequently, the normalized view-specific graphs are adaptively fused and factorized into the final clustering indicator matrix by embedding the semi-non-negative decomposition within a one-stage framework. To reduce the computational complexity, EMCTGL is extended to an anchor-driven MVC through determining anchors based on an adaptive density-peak strategy. Effective optimization schemes are devised to solve these non-convex models. Extensive experiments on various real-world datasets demonstrate that EMCTGL outperforms current state-of-the-art techniques.

Multi-view clustering, which uses information from multiple views to partition data into distinct clusters, has garnered significant attention. Existing MLP-based and GCN-based algorithms primarily focus on enhancing performance by extracting node attribute and graph structure features, and then integrating them for clustering. However, features extracted by MLP and GCN may differ in quality due to the high sparsity and noise in multi-view data. Directly integrating these features can lead to feature contamination. To address this issue, we propose a novel mutual calibration network for multi-view clustering (McMVC). Specifically, the attribute and structural features from multi-view data are integrated separately using the attention fusion module. A classifier is then employed to obtain high-confidence pseudo-labels for these fused features. We design a Cluster-level Mutual Calibration (CLMC) module that uses the pseudo-labels to mutually calibrate view features while maintaining compact cluster structures. During training, the attribute and structural features are not directly integrated to avoid feature contamination but are jointly optimized by reliable class information. Concurrently, we construct a Centroid-level Contrastive Calibration (CLCC) module to map view features into their inner centroid space and learn more discriminative centroid representations. Our approach outperforms state-of-the-art methods in multi-view data clustering, as demonstrated by extensive experiments on six real-world benchmark datasets. The source code is available at https://github.com/YuangXiao/ McMVC.

Federated Learning (FL) offers collaborative model training across multiple decentralized devices without the need to share data directly, enhancing privacy and data security. However, FL systems are susceptible to backdoor attacks, where malicious clients inject poisoned weights during training. Existing defenses, primarily based on anomaly detection, are prone to erroneous rejections of normal weights while accepting poisoned ones, largely due to shortcomings in quantifying similarities among client models. Furthermore, other defenses demonstrate effectiveness only when dealing with a limited number of malicious clients, typically fewer than 10%. To alleviate these vulnerabilities, we present G2uardFL, a protective framework that translates the detection of malicious clients into an attributed graph clustering problem, thus safeguarding FL systems. Specifically, this framework employs a client graph clustering approach to identify malicious clients and integrates an adaptive mechanism to amplify the discrepancy between the aggregated model and the poisoned ones, effectively eliminating embedded backdoors. Through empirical evaluation, comparing G2uardFL with cutting-edge defenses, such as FLAME (USENIX Security 2022) [37] and DeepSight (NDSS 2022) [43], against various backdoor attacks, including 3DFed (SP 2023) [26], our results demonstrate its significant effectiveness in mitigating backdoor attacks while having a negligible impact on the aggregated model’s performance on benign samples (i.e., the primary task performance). For instance, in an FL system with 25% malicious clients, G2uardFL reduces the attack success rate to 10.61%, while maintaining a primary task performance of 80.98% on the CIFAR-10 dataset. This surpasses the performance of the best-performing baseline, which merely achieves the attack success rate of 19.54%.

Subgraph Federated Learning (FL) has emerged as a promising paradigm for node classification tasks wherein subgraphs derived from a global graph are distributed across multiple devices to mitigate data leakage risks. Similar to other FL systems, subgraph FL faces significant security challenges, particularly from backdoor attacks, an area that remains extensively underexplored. Existing attacks typically follow a two-phase strategy to implant backdoors. However, in subgraph FL, such attacks often lead toDivergence Amplification, a phenomenon characterized by significant parameter discrepancies between normal and backdoored models, thereby compromising attack stealthiness. To tackle this challenge, we propose BEEF, a Backdoor attack with an End-to-End Framework designed for effectiveness, stealth, and durability. Unlike conventional methods, BEEF incorporates a dedicated trigger generator, which is jointly trained with a backdoored model. To increase its stealthiness, BEEF crafts adversarial perturbations as triggers that provoke misclassification while leaving the model’s parameters entirely untouched. Furthermore, by calibrating a subset of low-salience parameters associated with backdoor activation, BEEF ensures stable performance and sustained effectiveness across FL rounds. Comprehensive evaluations across eight datasets, four models, five state-of-the-art attacks, and six aggregation methods demonstrate BEEF’s effectiveness in deceiving GNNs while maintaining minimal impact on normal data performance. Additionally, we adapt BEEF to federated graph classification tasks, broadening its applicability and practicality.

Out-of-distribution (OOD) detection plays a crucial role as a mechanism for handling anomalies in computer vision systems. Among existing approaches, outlier exposure (OE), which trains the model with an additional auxiliary OOD dataset, has demonstrated strong effectiveness. However, acquiring clean and well-curated auxiliary OOD data is often infeasible, particularly within large and complex systems. Alternatively, wild outliers, i.e., unlabeled samples collected directly in deployment environments, are abundant and easy to obtain, and recent studies have shown that they can substantially benefit OOD detection learning. Nevertheless, wild outliers typically contain a mixture of in-distribution (ID) and OOD samples. Directly using them as auxiliary OOD data unavoidably exposes the model to adverse supervision signals arising from the contained ID samples. Yet existing methods still lack an effective strategy that can fully leverage wild outliers while suppressing the negative influence introduced by their ID subset. To this end, we propose a simple yet effective method named Clustering for Wild Outlier Exposure (C-WOE), which alleviates the adverse effect of the ID samples contained within wild outliers by reweighting them. Specifically, C-WOE assigns higher weights to real OOD samples and lower weights to ID samples and dynamically updates these weights during training. Theoretically, we establish solid guarantees for the proposed method. Empirically, extensive experiments conducted on various real-world benchmarks and simulated datasets demonstrate that C-WOE notably achieves superior performance compared with state-of-the-art methods, validating its reliability in image processing applications.

Tensor-based multi-view clustering has been widely studied to capture high-order correlations among multiple views. Nevertheless, existing tensorial methods still exhibit several limitations. First, many approaches rely on full similarity graphs, leading to quadratic or cubic complexity in the number of samples and poor scalability. Second, view-specific anchor graphs are often tensorized without cross-view anchor alignment, yielding structurally inconsistent tensor representations and reduced cross-view comparability. Third, low-rank regularization is typically imposed via the tensor nuclear norm (TNN), which uniformly shrinks singular values and may bias the estimation of the intrinsic tensor rank. To this end, we propose a novel framework, named Align then Tensorize: Multi-level Consistent Anchor Graph Learning for Scalable Multi-View Clustering (ATTMVC). It adopts an anchor-based graph learning framework in which each view is reconstructed from a small set of anchors with sample-wise sparse noise, substantially reducing computational complexity. Unlike existing tensor-based methods that directly tensorize unaligned view-wise anchor graphs, ATTMVC first aligns view-specific anchor graphs into a shared latent space, thereby enforcing structural consistency across views and enabling more reliable modeling of cross-view higher-order correlations. Furthermore, we introduce a Threshold Tensor Rank (TTR) surrogate on the aligned anchor graph tensor, which effectively promotes low-rank structure while mitigating the over-shrinking effect commonly caused by TNN-based regularization. Finally, extensive experiments demonstrate that ATTMVC outperforms state-of-the-art multi-view clustering methods. The code is publicly available at https://github.com/tangchuan2000/ATTMVC.

Industrial image anomaly detection (IAD) is a pivotal topic with huge value. Due to the nature of anomalies, real anomalies in a specific modern industrial domain (i.e., domain-specific anomalies) are usually too rare to collect, which severely hinders IAD. Thus, zero-shot anomaly synthesis (ZSAS), which synthesizes pseudo anomaly images without any domain-specific anomaly, emerges as a vital technique for IAD. However, existing solutions are either unable to synthesize authentic pseudo anomalies, or require cumbersome training. Thus, we focus on ZSAS and propose a brand-new paradigm that can realize both authentic and training-free ZSAS. It is based on a chronically-ignored fact: Although domain-specific anomalies are rare, real anomalies from other domains (i.e., cross-domain anomalies) are actually abundant and directly applicable to ZSAS. Specifically, our new ZSAS paradigm makes three-fold contributions: First, we propose a novel method named Cross-domain Anomaly Injection (CAI), which directly exploits cross-domain anomalies to enable highly authentic ZSAS in a training-free manner. Second, to supply CAI with sufficient cross-domain anomalies, we build the first Domain-agnostic Anomaly Dataset (DAAD) within our best knowledge, which provides ZSAS with abundant real anomaly patterns. Third, we propose a CAI-guided Diffusion Mechanism, which can further break the quantity limit of real anomalies and enable unlimited anomaly synthesis. Our head-to-head comparison with existing ZSAS solutions justifies the superior performance of our paradigm for IAD and demonstrates it as an effective and pragmatic ZSAS solution.

Federated learning is a promising bridge that connects machine learning methods and multi-central medical data. It trains models using the local data, and protects the privacy of data. There are many methods for federated learning to aggregate models, especially personalized methods, which show relatively excellent performance. However, most of them excessively pay attention to global and local information while ignoring the random components during aggregating. That limits their performance in metrics like accuracy, specificity, and sensitivity. We propose a method (denoted by FedDiv) to make a balance between these metrics. The basic idea is to extract centralized features meanwhile filtering random components, and conduct personalized aggregation. These centralized features draw encoders’ attention, which enhances the performance of personalized models in specificity and sensitivity. Besides, they contain more global and local information, which is advantageous for personalized aggregation. Meanwhile, our personalized method preserves the local information as far as possible during aggregating models. These local information are the critical factor for the personalized models to perform better in accuracy. Finally, we validate this method in three public and one private medical datasets. Comparing with 14 federated methods, our method achieves the best performance in metrics including accuracy, specificity, sensitivity, and F1 score.

Multi-view clustering (MVC) leverages complementary information across heterogeneous views to improve unsupervised partitioning. Nevertheless, the majority of existing MVC methods critically assume that samples are fully aligned across views, an assumption frequently violated in practice when multi-view data are collected from independent sources without any correspondence. This gives rise to Completely Unaligned multi-view Clustering (CUC), where cross-view sample correspondences are entirely unknown, fundamentally impeding effective multi-view fusion. Prior CUC-oriented methods typically infer inter-view relations from distance/similarity matrices; however, severe cross-view heterogeneity often induces over-smoothing in such matrices, leading to unreliable matching signals and degraded clustering performance. To address these issues, we propose Cross-view Graph Matching for Completely Unaligned multi-view Clustering (CGM-CUC), a unified framework that couples structure-aware representation learning with progressive cross-view alignment. Specifically, CGM-CUC introduces a bipartite graph-based sample re-encoding mechanism to enhance discriminative structural cues, and an iterative cross-view matching network that progressively refines permutation matrices to recover latent correspondences. Moreover, we develop an alignment-guided optimization strategy that mitigates the over-smoothing effect in similarity estimation, thereby stabilizing the matching process and improving downstream clustering. Extensive experiments on multiple benchmark datasets demonstrate that CGM-CUC consistently achieves superior performance over state-of-the-art baselines, with particularly notable gains under fully unaligned view settings.

Multimodal clustering (MMC) overcomes the limitations of unimodal methods by integrating information from multiple sources, but the complexity of heterogeneous information coupling hinders effective feature extraction. Critically, existing MMC paradigms primarily focus on capturing consensus through coarse-grained cross-modal alignment. However, such task-agnostic strategies overlook the differences in the utility of feature information across varying task environments. In the absence of task-centric guidance, models often struggle to effectively distinguish task-relevant critical information from task-irrelevant redundant noise during the disentanglement process, leading to information confusion in the representation space. To address this challenge, we propose a deep disentangled multimodal clustering method guided by information theory, named DRLMMC, which employs a tripartite information optimization mechanism to achieve deep disentanglement of cross-modal representations. 1) We design modality-specific encoders to construct nonlinear mapping spaces, transforming the reconstruction mechanism of autoencoders into an information-theoretic mutual information (MI) constraint problem, preserving the unique features of different modalities; 2) To establish cross-modal semantic associations, it constructs a cross-modal shared information extraction module, and, based on an information-theoretic framework, designs an optimization objective function to progressively align multimodal feature subspaces through MI maximization and contrastive learning, capturing task-relevant invariant features across modalities; 3) A unique information dynamic perception module is proposed, which employs a conditional MI projection network combined with learning distribution regularization to adaptively extract and enhance modality-specific task-relevant unique information. Experimental results demonstrate that DRLMMC outperforms existing state-of-the-art methods on multimodal benchmark datasets, exhibiting excellent generalization ability. Notably, it achieves precise disentanglement of cross-omics features in multi-omics analysis, offering a novel methodological approach for handling complex biomedical data.

Graph clustering, which aims to divide nodes in the graph into several distinct clusters, is a fundamental yet challenging task. Benefiting from the powerful representation capability of deep learning, deep graph clustering methods have achieved great success in recent years. However, the corresponding survey paper is relatively scarce, and it is imminent to make a summary of this field. From this motivation, we conduct a comprehensive survey of deep graph clustering. Firstly, we introduce formulaic definition, evaluation, and development in this field. Secondly, the taxonomy of deep graph clustering methods is presented based on four different criteria, including graph type, network architecture, learning paradigm, and clustering method. Thirdly, we carefully analyze the existing methods via extensive experiments and summarize the challenges and opportunities from five perspectives, including graph data quality, stability, scalability, discriminative capability, and unknown cluster number. Besides, the applications of deep graph clustering methods in six domains, including computer vision, natural language processing, recommendation systems, social network analyses, bioinformatics, and medical science, are presented. Last but not least, this paper provides open resource supports, including 1) a collection (https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering) of state-of-the-art deep graph clustering methods (papers, codes, and datasets) and 2) a flexible and extensible Python library (https://github.com/Marigoldwu/PyDGC) for deep graph clustering. We hope this work can serve as a quick guide and help researchers overcome challenges in this vibrant field.

Multi-view clustering aims to leverage complementary information from multiple data sources to improve clustering quality. Traditional graph-based Non-k multi-view clustering methods enable automatic cluster number determination but suffer from severe scalability issues due to their reliance on constructing large sample-level affinity graphs with quadratic complexity. To address this limitation, we propose a novel scalable Non-k Multi-View Clustering framework via Inter-Anchor Graph learning (MVC-IAG). Our method first extracts a small set of representative anchors via k-means on concatenated multi-view features, then learns a unified inter-anchor graph by integrating multi-view structural information and feature similarity priors. Our framework performs Non-k cluster discovery directly on this compact, learned inter-anchor graph, thereby enabling automatic cluster number determination, and subsequently propagates the results to all samples. Extensive experiments on multiple large scale datasets demonstrate that MVC-IAG significantly reduces computational cost while achieving competitive or superior clustering performance compared to state-of-the-art Non-k multi view clustering approaches.

Anchor graph learning has become a widely used technique for significantly reducing the computational complexity in existing multi-view clustering methods. However, most existing approaches select anchors independently for each view and then generate the consensus graph by directly fusing all anchor graphs. This process overlooks the correspondence between anchor sets across different views, i.e., the column order correspondence of the anchor graphs. To address this limitation, we propose a novel anchor-based tensor multi-rank constraint multi-view clustering method (TMC). Specifically, TMC captures the high-order structural information of the original data by constructing an anchor graph tensor and enforcing a multi-rank constraint to induce a block-diagonal structure. Additionally, to enhance anchor consistency across all view, we construct the anchor graph of each view into an anchor tensor and impose a low-rank constraint on it. In this way, the block-diagonal structure of each anchor graph maintains an approximate alignment between anchors. Furthermore, we provide theoretical proof that the generated anchor graphs inherently exhibit a block-diagonal structure. Extensive experimental results on six multi-view datasets demonstrate that TMC outperforms existing state-of-the-art methods, highlighting its effectiveness in multi-view clustering task.

Multi-View Clustering (MVC) has gained increasing attention due to its ability to effectively leverage the complementary information of multi-view data. Despite the success of existing MVC methods in many real-world applications, they often overlook the discrepancy of view-specific latent distribution and struggle to ensure the completeness of the multi-view data. To address these challenges and harness the powerful feature extraction capability of deep networks, we propose a novel Contrastive and Dual Adversarial Representation Learning method for Multi-view Clustering, termed as CDARL, to solve multi-view clustering problems with both complete and incomplete multi-view data. Specifically, CDARL employs alternating adversarial and contrastive learning to align the view-specific representations, driving them into the same semantic latent space to minimize the discrepancy in view-specific distributions. In addition, a consensus latent representation is learned by an adaptive fusion block that integrates information from multiple views. The consensus representation is further refined through adversarial learning modeling the transformation of the standard Gaussian distribution to the original data distribution. Moreover, the proposed method incorporates an imputation strategy designed to handle the incomplete multi-view data clustering task. This strategy utilizes both reconstructed samples and cross-view neighbors to impute missing views from the latent space and the original space, thereby preserving clustering information, which ensures the quality and feasibility of the imputed samples. Experimental results on six widely used datasets have verified the competitiveness of the proposed CDARL method against state-of-the-art methods in MVC problems with complete and incomplete multi-view data. Code is available athttps://github.com/xywy220/CDARL-MVC.

Spatially resolved transcriptomics (SRT) facilitates the simultaneous acquisition of gene expression profiles, spatial location, and histology images for spatial clustering analysis, providing transformative insights into cellular interactions and the underlying mechanisms of disease progression. Despite the success of existing research in spatial clustering tasks, most methods overlook the information imbalance arising among spots in intra- and inter-modal communication due to insufficient sequencing depth and modality discrepancies. To this end, we propose a novel multi-view information rebalance learning method for SRT data clustering, referred to as MIRL. Specifically, we construct hypergraphs for the gene and histological image modalities and leverage hypergraph neural networks to learn the hypergraph features, which helps mitigate the propagation of intra-modal information imbalance by capturing higher-order interactions among multiple spots, rather than relying solely on pairwise relationships in traditional feature graphs. To enhance the global coordination among spots and the interrelations between features across modalities, we perform intra-modal adaptive fusion of modality-specific hypergraph features and spatial features, followed by cross-modal integration. Furthermore, adaptive reconstruction of the cross-modal heterogeneous graph is employed to rebalance inter-modal information flow associated with pseudo-labels, ensuring more reliable information extraction by alleviating the impact of incorrect heterogeneous negative edges connections through the construction of hypergraph edges. Extensive experimental results demonstrate that the proposed MIRL achieves competitive performance in spatial domain identification compared to other state-of-the-art ones.

Knowledge graph reasoning (KGR) is an important task in data mining. It aims to mine the logical rules based on the existing facts and further infer new facts, which makes the graph complete and accurate. Currently, with the development of large language models (LLMs), they are widely integrated with different baseline models for better performance. A few works are proposed on LLM-enhanced KGR models, which leaves many issues to be addressed. Inspired by the efficiency and accuracy of LLM in generating text semantic information, this article proposes a KGR method based on LLM information enhancement and subgraph alignment (LSA). LSA first utilizes LLM to generate textual descriptions corresponding to graph entities, relationships, and subgraphs. Then, it utilizes the generated textual attribute in both explicit and implicit ways: 1) explicit utilization, treating LLM-generated text features as the initialized features for the previous KGR model; and 2) implicit utilization, aligning the structural and textual information of key subgraphs via a learning mechanism. Finally, LSA is evaluated on three typical datasets. The promising performances demonstrate that our LSA leverages LLM to make the KG for richer information, and the representation learning model is empowered with better expressive ability.

The field of knowledge graph representation learning (KGRL) has been rapidly expanding. To effectively apply KGRL models to large real-world knowledge graphs (KGs), anchor-based methods have been proposed. These methods aim to reduce computational costs and parameter requirements by encoding entities using a small set of entity anchors. However, existing anchor selection approaches are often rudimentary and sometimes yield suboptimal results. In this article, we propose a scalable anchor-based KGRL method called SKIP. By leveraging prototype information, our method selects representative entities as anchors. The SKIP method consists of two main steps. First, pretraining models are employed to encode entities by utilizing the topological structure and textual information in KGs. Second, the prototype learning module (PLM) extracts entity prototypes, which are then used to sample entity anchors that contain valuable prototype information. These settings enable SKIP to identify representative and reasonable entity anchors, leading to improved performance while requiring fewer computational resources. Extensive experiments conducted on various downstream tasks using KGs of different scales demonstrate the superiority and effectiveness of SKIP. Particularly, on the large OGB WikiKG 2 dataset, our method achieves comparable performance while reducing running time by approximately 21.28% and requiring 21.43% fewer model parameters compared to the baseline. This indicates the superior scalability of SKIP.

Federated learning (FL) facilitates collaborative training among multiple clients while preserving data privacy by eliminating raw data transmission. However, the inherent data heterogeneity among participants induces bias during collaborative learning, significantly degrading the performance of local models. Existing FL solutions face critical challenges in achieving efficient knowledge transmission, particularly with respect to insufficient information extraction or excessive communication costs, which result in slow convergence and inferior performance. To address these limitations, we propose a novel FL framework in a synergy of multi-level prototype-based contrastive learning (CL) and soft label generation, named FedMPS. The proposed method first constructs multi-level prototypes from different layers of the model to capture semantic information in high-level features and detailed information in low-level features. These prototypes are then utilized through CL to enhance intra-class discriminability and intra-class consistency in the feature space. In addition, a prototype-guided soft label generation module is introduced to model latent interclass relationships in the output space. Instead of exchanging model parameters, FedMPS transmits only prototypes and soft labels, effectively reducing global knowledge shift and communication costs. Extensive experimental studies on six publicly available datasets validate the effectiveness of the proposed method when compared to the current state-of-the-art FL approaches. The code is available at github.com/wenxinyang1026/FedMPS.

Imbalance in multi-domain multi-modal settings remains a significant challenge in real-world applications, such as fake news detection. Although existing methods have enhanced semantic representations and employed complex architectures to improve recognition performance, most of them focus on domain heterogeneity and modality sensitivity. However, these methods neglect the class imbalance, which severely impacts model robustness and generalization in open-world scenarios. Learning for such imbalanced multi-domain multi-modal data is crucial but rarely studied, particularly when the domain and modal of samples are imbalanced. To address these challenges, we propose a novel Imbalanced multi-domain multi-modal learning method with Expert Collaboration and Dynamic Fusion, named IECDF. Specifically, to alleviate inter-domain imbalance, we design an expert collaboration module with a domain-shared specific embedding structure and an improved gating strategy to enhance the discriminative power of the cross-domain features. Besides, a dynamic fusion mechanism based on Mamba-Former is designed to learn adaptive weights for each modality. Moreover, to tackle the intra-class imbalance problem, we adopt asymmetric re-weighted loss—DLINEX—to increase the contributions of minority class samples and learn the unbiased decision boundary. Extensive experimental results on various datasets validate the superiority of our proposed IECDF compared to state-of-the-art methods. Our code will be available at https://github.com/Yuchen-zh/IECDF .

Metric-based methods, such as ProtoNet, excel in few-shot image classification by encouraging similarity to class prototypes. However, prototypes built from limited samples often capture only partial class information, limiting performance. Recent distribution estimation-based methods attempt to enhance performance by leveraging similar base class distributions. Yet, these approaches struggle when the distributions of base and novel classes differ significantly. Empirical analysis reveals that conceptually related categories share a local-global semantic invariance even under large distribution gaps. Based on this insight, a Self-Regressive Prototype Refinement (SRPR) is proposed to address the issue of incomplete prototype representations in few-shot learning. SRPR estimates an optimization direction for local embeddings, progressively refining them toward more global representations by exploiting local-global semantic invariance in base class data. The conservative use of coarse-grained local-global semantic structures, rather than relying on similar distributions, enhances SRPR’s applicability. With minimal computational overhead per refinement step, SRPR significantly improves classification performance and achieves state-of-the-art results across multiple few-shot benchmarks, particularly in the challenging 1-shot setting. Code is available at: https://github.com/giraffe2021/SRPR .

Anchor selection or learning has become a critical component in large-scale multi-view clustering. Existing anchor-based methods, which either select-then-fix or initialize-then-optimize with orthogonality, yield promising performance. However, these methods still suffer from instability of initialization or insufficient depiction of data distribution. Moreover, the desired properties of anchors in multi-view clustering remain unspecified. To address these issues, this paper first formalizes the desired characteristics of anchors, namely Diversity, Balance and Compactness. We then devise and mathematically validate anchors that satisfy these properties by maximizing the Mahalanobis distance between anchors. Furthermore, we introduce a novel method called Max-Mahalanobis Anchors Guidance for multi-view Clustering (MAGIC), which guides the cross-view representations to progressively align with our well-defined anchors. This process yields highly discriminative and compact representations, significantly enhancing the performance of multi-view clustering. Experimental results show that our meticulously designed strategy significantly outperforms existing anchor-based methods in enhancing anchor efficacy, leading to substantial improvement in multi-view clustering performance.

Existing Multiple Kernel Clustering (MKC) algorithms commonly utilize the Nyström method to handle large-scale datasets. However, most of them employ uniform sampling for kernel matrix approximation, hence failing to accurately capture the underlying data structure, leading to large approximation errors. Additionally, they often use the same landmark points for all kernel matrix approximations, reducing kernel diversity. Moreover, in scenarios where approximate kernel matrices emerge over time, these methods require storing historical kernel information and recalculating, resulting in inefficient resource utilization. To address these issues, we propose a novel MKC algorithm, termed Incremental Nyström-based Multiple Kernel Clustering (INMKC). Specifically, leverage score sampling is utilized to reduce kernel approximation errors and enhance kernel diversity. Furthermore, we employ a consensus clustering structure that aligns with the newly emerged base kernel matrix for updates, avoiding recalculating previous kernel matrices, thus saving substantial computational resources. Additionally, we tackle the challenge of aligning incremental approximate kernels with different landmark points. Extensive experiments on the proposed INMKC demonstrate its effectiveness and efficiency compared to state-of-the-art methods.

Multi-view clustering (MVC) for remote sensing data is a critical and challenging task in Earth observation. Although recent advances in graph neural network (GNN)-based MVC have shown remarkable success, the most prevalent approaches have two major limitations: 1) heavily relying on a predefined yet fixed graph, which limits the performance of clustering because the large number of indistinguishable background samples contained in remote sensing data would introduce noise information and increase structure heterogeneity; 2) ignoring the effect of confusing samples on cluster structure compactness, which leads to fluffy cluster structure and decrease feature discriminability. To address these issues, we propose a Structure-Adaptive Multi-View Graph Clustering method named SAMVGC on remote sensing data which boosts the structure homogeneity and cluster compactness by adaptively learning the graph and cluster structures, respectively. Concretely, we use the geometric structure within the feature embedding space to refine adjacency matrices. The adjacency matrices are dynamically fused with the previous ones to improve the homogeneity and stability of structure information. Additionally, the samples are separated into two categories, including the central (intra-cluster center samples) and the confusing (inter-cluster boundary samples). On the basis, we deploy the contrastive learning paradigm on the central samples within views and the consistent learning paradigm on the confusing samples between views, improving the cluster compactness and consistency. Finally, we conduct extensive experiments on four benchmarks and achieve promising results, well demonstrating the effectiveness and superiority of the proposed method.

Text-based knowledge graph completion methods take advantage of pre-trained language models (PLM) to enhance intrinsic semantic connections of raw triplets with detailed text descriptions. Typical methods in this branch map an input query (textual descriptions associated with an entity and a relation) and its candidate entities into feature vectors, respectively, and then maximize the probability of valid triples. These methods are gaining promising performance and increasing attention for the rapid development of large language models. According to the property of the language models, the more related and specific context information the input query provides, the more discriminative the resultant embedding will be. In this paper, through observation and validation, we find a neglected fact that the relation-aware neighbors of the head entities in queries could act as effective contexts for more precise link prediction. Driven by this finding, we propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC). Specifically, in our method, to provide a reference of what might the target entity be like, we first generate anchor entities within the relation-aware neighborhood of the head entity. Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching. The results of our extensive experiments not only validate the efficacy of RAA-KGC but also reveal that by integrating our relation-aware anchor enhancement strategy, the performance of current leading methods can be notably enhanced without substantial modifications.

Shilong Pan, Zhiliang Tian, Zhen Huang, Wanlong Yu, Zhihua Wen, Xinwang Liu, Kai Lu, Minlie Huang, Dongsheng Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Multi-view clustering is a long-standing hot topic in machine learning communities, due to its capability of integrating data information from multiple sources and modalities. By utilizing tensor Singular Value Decomposition (t-SVD) technique with the tensor rotation trick, recent advances have achieved remarkable improvements on clustering performance. However, we find this is attributed to the inadvertent use of sequential information of sorted data samples, i.e. inadvertent label use, which violates the unsupervised learning setting. On the other hand, existing large-scale approaches are mostly developed on the basis of matrix factorization or anchor techniques, thereby fail to consider the similarities among all data samples, preventing from further performance improvement. To address the above issues, we first analyze the tensor rotation trick and recommend to remove it from tensor clustering. On its basis, a novel large-scale multi-view tensor clustering method is developed by incorporating the pair-wise similarities with implicit linear kernel function. To solve the resultant optimization problem, we design an efficient algorithm of linear complexity. Moreover, extensive experiments are conducted and corresponding results well support the aforementioned finding and validate the effectiveness and efficiency of the proposed method.

In incomplete multi-view clustering (IMVC), missing data induce prototype shifts within views and semantic inconsistencies across views. A feasible solution is to explore cross-view consistency in paired complete observations, further imputing and aligning the similarity relationships inherently shared across views. Nevertheless, existing methods are constrained by two-tiered limitations: (1) Neither instance- nor cluster-level consistency learning construct a semantic space shared across views to learn consensus semantics. The former enforces cross-view instances alignment, and wrongly regards unpaired observations with semantic consistency as negative pairs; the latter focuses on cross-view cluster counterparts while coarsely handling fine-grained intra-cluster relationships within views. (2) Excessive reliance on consistency results in unreliable imputation and alignment without incorporating view-specific cluster information. Thus, we propose an IMVC framework, imputation- and alignment-free for consensus semantics learning (FreeCSL). To bridge semantic gaps across all observations, we learn consensus prototypes from available data to discover a shared space, where semantically similar observations are pulled closer for consensus semantics learning. To capture semantic relationships within specific views, we design a heuristic graph clustering based on modularity to recover cluster structure with intra-cluster compactness and inter-cluster separation for cluster semantics enhancement. Extensive experiments demonstrate, compared to state-of-the-art competitors, FreeCSL achieves more confident and robust assignments on IMVC task.

Multi-view clustering aims to improve clustering accuracy by effectively integrating complementary information from multiple perspectives. However, existing methods often encounter challenges such as feature conflicts between views and insufficient enhancement of individual view features, which hinder clustering performance. To address these challenges, we propose a novel framework, EPFMVC, which integrates feature enhancement with progressive fusion to more effectively align multi-view data. Specifically, we introduce two key innovations: (1) a Feature Channel Attention Encoder (FCAencoder), which adaptively enhances the most discriminative features in each view, and (2) a View Graph-based Progressive Fusion Mechanism, which constructs a view graph using optimal transport (OT) distance to progressively fuse similar views while minimizing inter-view conflicts. By leveraging multi-head attention, the fusion process gradually integrates complementary information, ensuring more consistent and robust shared representations. These innovations enable superior representation learning and effective fusion across views. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art techniques, achieving notable improvements in multi-view clustering tasks across various datasets and evaluation metrics.

Multi-view clustering (MVC) has emerged as a leading paradigm in unsupervised learning, gaining significant attention. Central to this framework is the concept of view-pair contrastive learning, which aims to maximize mutual information between pairs of views, thereby facilitating consistent latent representations. Nevertheless, two critical challenges remain: i) Identifying the most suitable pairs of views for contrastive learning becomes difficult when more than two views are available, especially in the absence of prior knowledge; ii)Including all available views in contrastive learning can degrade performance due to the presence of low-quality views. To address these issues, we propose a novel mechanism, EASEMVC(Efficient DuAl Selection MEchanism for Deep Multi-View Clustering). EASEMVC begins by constructing a view graph using the Optimal Transport (OT) distance between bipartite graphs of individual views. A view selection module is then designed to perform efficient view-level selection based on the topological relationships within the view graph. Additionally, a cross-view sample graph is built at the sample level, where the topological relationships among samples are used to generate reliable learning weights. Leveraging the selected view pairs and sample weights, contrastive learning is employed to obtain consistent representations across views. Extensive experiments across six benchmark datasets demonstrate that EASEMVC outperforms current state-of-the-art methods.

Chain-of-thought (CoT) distillation allows a large language model (LLM) to guide a small language model (SLM) in reasoning tasks.Existing methods train the SLM to learn the long rationale in one iteration, resulting in two issues: 1) Long rationales lead to a large tokenlevel batch size during training, making gradients of core reasoning tokens (i.e., the token will directly affect the correctness of subsequent reasoning) over-smoothed as they contribute a tiny fraction of the rationale.As a result, the SLM converges to sharp minima where it fails to grasp the reasoning logic.2) The response is slow, as the SLM must generate a long rationale before reaching the answer.Therefore, we propose chunk-wise training (CWT), which uses a heuristic search to divide the rationale into internal semantically coherent chunks and focuses SLM on learning from only one chunk per iteration.In this way, CWT naturally isolates non-reasoning chunks that do not involve the core reasoning token (e.g., summary and transitional chunks) from the SLM learning for reasoning chunks, making the fraction of the core reasoning token increase in the corresponding iteration.Based on CWT, skip-thinking training (STT) is proposed.STT makes the SLM automatically skip nonreasoning medium chunks to reach the answer, improving reasoning speed while maintaining accuracy.We validate our approach on a variety of SLMs and multiple reasoning tasks.

Qiunan Du, Zhiliang Tian, Zhen Huang, Kailun Bian, Tianlun Liu, Zhaoning Zhang, Xinwang Liu, Feng Liu, Dongsheng Li. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Multi-view clustering leverages complementary representations from diverse sources to enhance performance. However, real-world data often suffer incomplete cases due to factors like privacy concerns and device malfunctions. A key challenge is effectively utilizing available instances to recover missing views. Existing methods frequently overlook the heterogeneity among views during recovery, leading to significant distribution discrepancies between recovered and true data. Additionally, many approaches focus on cross-view correlations, neglecting insights from intra-view reliable structure and cross-view clustering structure. To address these issues, we propose BURG, a novel method for incomplete multi-view clustering with distriBution dUal-consistency Recovery Guidance. We treat each sample as a distinct category and perform cross-view distribution transfer to predict the distribution space of missing views. To compensate for the lack of reliable category information, we design a dual-consistency guided recovery strategy that includes intra-view alignment guided by neighbor-aware consistency and cross-view alignment guided by prototypical consistency. Extensive experiments on benchmarks demonstrate the superiority of BURG in the incomplete multi-view scenario.

In this paper, we address the problem of novel class discovery (NCD), which aims to cluster novel classes by leveraging knowledge from disjoint known classes. While recent advances have made significant progress in this area, existing NCD methods face two major limitations. First, they primarily focus on single-view data (e.g., images), overlooking the increasingly common multi-view data, such as multi-omics datasets used in disease diagnosis. Second, their reliance on pseudo-labels to supervise novel class clustering often results in unstable performance, as pseudo-label quality is highly sensitive to factors such as data noise and feature dimensionality. To address these challenges, we propose a novel framework named Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery (IICMVNCD), which is the first attempt to explore NCD in multi-view setting so far. Specifically, at the intra-view level, leveraging the distributional similarity between known and novel classes, we employ matrix factorization to decompose features into view-specific shared base matrices and factor matrices. The base matrices capture distributional consistency among the two datasets, while the factor matrices model pairwise relationships between samples. At the inter-view level, we utilize view relationships among known classes to guide the clustering of novel classes. This includes generating predicted labels through the weighted fusion of factor matrices and dynamically adjusting view weights of known classes based on the supervision loss, which are then transferred to novel class learning. Experimental results validate the effectiveness of our proposed approach.

Multi-view clustering (MVC) aims to explore the common clustering structure across multiple views. Many existing MVC methods heavily rely on the assumption of view consistency, where alignments for corresponding samples across different views are ordered in advance. However, real-world scenarios often present a challenge as only partial data is consistently aligned across different views, restricting the overall clustering performance. In this work, we consider the model performance decreasing phenomenon caused by data order shift (i.e., from fully to partially aligned) as a generalized multi-view clustering problem. To tackle this problem, we design a causal multi-view clustering network, termed CauMVC. We adopt a causal modeling approach to understand multi-view clustering procedure. To be specific, we formulate the partially aligned data as an intervention and multi-view clustering with partially aligned data as an post-intervention inference. However, obtaining invariant features directly can be challenging. Thus, we design a Variational Auto-Encoder for causal learning by incorporating an encoder from existing information to estimate the invariant features. Moreover, a decoder is designed to perform the post-intervention inference. Lastly, we design a contrastive regularizer to capture sample correlations. To the best of our knowledge, this paper is the first work to deal generalized multi-view clustering via causal learning. Empirical experiments on both fully and partially aligned data illustrate the strong generalization and effectiveness of CauMVC.

With the rapid growth of multimodal and multi-view data, multi-view bipartite graph clustering (MVBGC) has emerged as a promising solution for large-scale tasks, which with linear complexity. However, most methods adhere to a unidirectional “encoding” design, where the bipartite graph is directly constructed from input data. Enlightened by the prevalent encoding-decoding in deep learning, this paper rethinks existing paradigms and proposes a novel “auto-encoding” MVBGC framework, named BGAE. Our model seamlessly integrates encoding, bipartite graph learning, and decoding modules within a self-supervised learning framework. The encoding module extracts a joint representation from input data, the bipartite graph learning module learns a discriminative bipartite graph in latent semantic space, and the decoding module reconstructs the input data by the structural information. Extensive experiments verify the superiority of our novel design, particularly highlighting the critical role of “decoding” learning. This work represents the first attempt to explore encoding-decoding design in MVBGC.

Anchor-based multi-view graph clustering has recently gained popularity as an effective approach for clustering data with multiple views. However, existing methods have limitations in terms of handling inconsistent information and noise across views, resulting in an unreliable consensus representation. Additionally, post-processing is needed to obtain final results after anchor graph construction, which negatively affects clustering performance. In this paper, we propose a Robust and Consistent Anchor Graph Learning method (RCAGL) for multi-view clustering to address these challenges. RCAGL constructs a consistent anchor graph that captures inter-view commonality and filters out view-specific noise by learning a consistent part and a view-specific part simultaneously. A k-connectivity constraint is imposed on the consistent anchor graph, leading to a clear graph structure and direct generation of cluster labels without additional post-processing. Experimental results on several benchmark datasets demonstrate the superiority of RCAGL in terms of clustering accuracy, scalability to large-scale data, and robustness to view-specific noise, outperforming advanced multi-view clustering methods. Our code is publicly available at https://github.com/Tracesource/RCAGL.

Benefiting from the strong reasoning capabilities, Large language models (LLMs) have demonstrated remarkable performance in recommender systems. Various efforts have been made to distill knowledge from LLMs to enhance collaborative models, employing techniques like contrastive learning for representation alignment. In this work, we prove that directly aligning the representations of LLMs and collaborative models is suboptimal for enhancing downstream recommendation tasks performance, based on the information theorem. Consequently, the challenge of effectively aligning semantic representations between collaborative models and LLMs remains unresolved. Inspired by this viewpoint, we propose a novel plug-and-play alignment framework for LLMs and collaborative models. Specifically, we first disentangle the latent representations of both LLMs and collaborative models into specific and shared components via projection layers and representation regularization. Subsequently, we perform both global and local structure alignment on the shared representations to facilitate knowledge transfer. Additionally, we theoretically prove that the specific and shared representations contain more pertinent and less irrelevant information, which can enhance the effectiveness of downstream recommendation tasks. Extensive experimental results on benchmark datasets demonstrate that our method is superior to existing state-of-the-art algorithms.

Most of incomplete multi-view clustering (IMVC) methods typically choose to ignore the missing samples and only utilize observed unpaired samples to construct bipartite similarity. Moreover, they employ a single quantity of prototypes to extract the information of $\textbf{all}$ views. To eliminate these drawbacks, we present a simple yet effective IMVC approach, SIIHPC, in this work. It firstly transforms partial bipartition learning into original sample form by virtue of reconstruction concept to split out of observed similarity, and then loosens traditional non-negative constraints via regularizing samples to more freely characterize the similarity. Subsequently, it learns to recover the incomplete parts by utilizing the connection built between the similarity exclusive on respective view and the consensus graph shared for all views. On this foundation, it further introduces a group of hybrid prototype quantities for each individual view to flexibly extract the data features belonging to each view itself. Accordingly, the resulting graphs are with various scales and describe the overall similarity more comprehensively. It is worth mentioning that these all are optimized in one unified learning framework, which makes it possible for them to reciprocally promote. Then, to effectively solve the formulated optimization problem, we design an ingenious auxiliary function that is with theoretically proven monotonic-increasing properties. Finally, the clustering results are obtained by implementing spectral grouping action on the eigenvectors of stacked multi-scale consensus similarity. Experimental results confirm the effectiveness of SIIHPC.

Recent advancements in multiple kernel clustering (MKC) have highlighted the effectiveness of late fusion strategies, particularly in enhancing computational efficiency to near-linear complexity while achieving promising clustering performance. However, existing methods encounter three significant limitations: (1) reliance on fixed base partition matrices that do not adaptively optimize during the clustering process, thereby constraining their performance to the inherent representational capabilities of these matrices; (2) a focus on adjusting kernel weights to explore inter-view consistency and complementarity, which often neglects the intrinsic high-order correlations among views, thereby limiting the extraction of comprehensive multiple kernel information; (3) a lack of adaptive mechanisms to accommodate varying distributions within the data, which limits robustness and generalization. To address these challenges, this paper proposes a novel algorithm termed Dynamic Late Fusion Multiple Kernel Clustering with Robust {Tensor Learning via min-max optimization (DLEFT-MKC), which effectively overcomes the representational bottleneck of base partition matrices and facilitates the learning of meaningful high-order cross-view information. Specifically, it is the first to incorporate a min-max optimization paradigm into tensor-based MKC, enhancing algorithm robustness and generalization. Additionally, it dynamically reconstructs decision layers to enhance representation capabilities and subsequently stacks the reconstructed representations for tensor learning that promotes the capture of high-order associations and cluster structures across views, ultimately yielding consensus clustering partitions. To solve the resultant optimization problem, we innovatively design a strategy that combines reduced gradient descent with the alternating direction method of multipliers, ensuring convergence to local optima while maintaining high computational efficiency. Extensive experimental results across various benchmark datasets validate the superior effectiveness and efficiency of the proposed DLEFT-MKC.

Multi-kernel clustering (MKC) has emerged as a powerful method for capturing diverse data patterns, offering robust and generalized representations of data structures. However, the increasing deployment of MKC in real-world applications raises concerns about its vulnerability to adversarial perturbations. While adversarial robustness has been extensively studied in other domains, its impact on MKC remains largely unexplored. In this paper, we address the challenge of assessing the adversarial robustness of MKC methods in a black-box setting. Specifically, we propose *AdvMKC*, a novel reinforcement-learning-based adversarial attack framework designed to inject imperceptible perturbations into data and mislead MKC methods. AdvMKC leverages proximal policy optimization with an advantage function to overcome the instability of clustering results during optimization. Additionally, it introduces a generator-clusterer framework, where a generator produces adversarial perturbations, and a clusterer approximates MKC behavior, significantly reducing computational overhead. We provide theoretical insights into the impact of adversarial perturbations on MKC and validate these findings through experiments. Evaluations across seven datasets and eleven MKC methods (seven traditional and four robust) demonstrate AdvMKC's effectiveness, robustness, and transferability.

Deep graph clustering (DGC), which aims to unsupervisedly separate the nodes in an attribute graph into different clusters, has seen substantial potential in various industrial scenarios like community detection and recommendation. However, the real-world attribute graphs, e.g., social networks interactions, are usually large-scale and attribute-missing. To solve these two problems, we propose a novel DGC method termed **C**omplementary **M**ulti-**V**iew **N**eighborhood **D**ifferentiation ($\textit{CMV-ND}$), which preprocesses graph structural information into multiple views in a complete but non-redundant manner. First, to ensure completeness of the structural information, we propose a recursive neighborhood search that recursively explores the local structure of the graph by completely expanding node neighborhoods across different hop distances. Second, to eliminate the redundancy between neighborhoods at different hops, we introduce a neighborhood differential strategy that ensures no overlapping nodes between the differential hop representations. Then, we construct $K+1$ complementary views from the $K$ differential hop representations and the features of the target node. Last, we apply existing multi-view clustering or DGC methods to the views. Experimental results on six widely used graph datasets demonstrate that CMV-ND significantly improves the performance of various methods.

Inspired by the well-known coreset in clustering algorithms, we introduce the definition of the core kernel for multiple kernel clustering (MKC) algorithms. The core kernel refers to running MKC algorithms on smaller-scale base kernel matrices to obtain kernel weights similar to those obtained from the original full-scale kernel matrices. Specifically, the core kernel refers to a set of kernel matrices of size $\widetilde{\mathcal{O}}(1/\varepsilon^2)$ that perform MKC algorithms on them can achieve a $(1+\varepsilon)$-approximation for the kernel weights. Subsequently, we can leverage approximated kernel weights to obtain a theoretically guaranteed large-scale extension of MKC algorithms. In this paper, we propose a core kernel construction method based on singular value decomposition and prove that it satisfies the definition of the core kernel for three mainstream MKC algorithms. Finally, we conduct experiments on several benchmark datasets to verify the correctness of theoretical results and the efficiency of the proposed method.

Multi-view clustering (MVC) leverages complementary information from diverse data sources to enhance clustering performance. However, its practical deployment in distributed and privacy-sensitive scenarios remains challenging. Federated multi-view clustering (FMVC) has emerged as a potential solution, but existing approaches suffer from substantial limitations, including excessive communication overhead, insufficient privacy protection, and inadequate handling of missing views. To address these issues, we propose Efficient Federated Incomplete Multi-View Clustering (EFIMVC), a novel framework that introduces a localized optimization strategy to significantly reduce communication costs while ensuring theoretical convergence. EFIMVC employs both view-specific and shared anchor graphs as communication variables, thereby enhancing privacy by avoiding the transmission of sensitive embeddings. Moreover, EFIMVC seamlessly extends to scenarios with missing views, making it a practical and scalable solution for real-world applications. Extensive experiments on benchmark datasets demonstrate the superiority of EFIMVC in clustering accuracy, communication efficiency, and privacy preservation. Our code is publicly available at https://github.com/Tracesource/EFIMVC.

Leveraging the powerful representation learning capabilities, deep multi-view clustering methods have demonstrated reliable performance by effectively integrating multi-source information from diverse views in recent years. Most existing methods rely on the assumption of clean views. However, noise is pervasive in real-world scenarios, leading to a significant degradation in performance. To tackle this problem, we propose a novel multi-view clustering framework for the automatic identification and rectification of noisy data, termed AIRMVC. Specifically, we reformulate noisy identification as an anomaly identification problem using GMM. We then design a hybrid rectification strategy to mitigate the adverse effects of noisy data based on the identification results. Furthermore, we introduce a noise-robust contrastive mechanism to generate reliable representations. Additionally, we provide a theoretical proof demonstrating that these representations can discard noisy information, thereby improving the performance of downstream tasks. Extensive experiments on six benchmark datasets demonstrate that AIRMVC outperforms state-of-the-art algorithms in terms of robustness in noisy scenarios. The code of AIRMVC are available at https://github.com/xihongyang1999/AIRMVC on Github.

Despite remarkable advances, existing incomplete multi-view clustering (IMC) methods typically leverage either perspective-shared or perspective-specific determinants to encode cluster representations. To address this limitation, we introduce a BACDL algorithm designed to explicitly capture both concurrently, thereby exploiting heterogeneous data more effectively. It chooses to bifurcate feature clusters and further alienate them to enlarge the discrimination. With distribution learning, it successfully couples view guidance into feature clusters to alleviate dimension inconsistency. Then, building on the principle that samples in one common cluster own similar marginal distribution and conditional distribution, it unifies the association between feature clusters and sample clusters to bridge all views. Thereafter, all incomplete sample clusters are reordered and mapped to a common one to formulate clustering embedding. Last, the overall linear overhead endows it with a resource-efficient characteristic.

Current multi-view clustering (MVC) techniques generally focus only on the relationship between anchors and samples, while overlooking that between anchors. Moreover, due to the lack of data labels, the cluster order is inconsistent across views and accordingly anchors encounter misalignment, which will confuse the graph structure and disorganize cluster representation. Even worse, it typically brings variance during forming spectral embedding, degenerating the stability of clustering results. In response to these concerns, in the paper we propose a MVC approach named DTP-SF-BVF. Concretely, we explicitly exploit the geometric properties between anchors via self-expression learning skill, and utilize topology learning strategy to feed captured anchor-anchor features into anchor-sample graph so as to explore the manifold structure hidden within samples more adequately. To reduce the misalignment risk, we introduce a permutation mechanism for each view to jointly rearrange anchors according to respective view characteristics. Besides not involving selecting the baseline view, it also can coordinate with anchors in the unified framework and thereby facilitate the learning of anchors. Further, rather than forming spectrum and then performing embedding partitioning, based on the criterion that samples and clusters should be hard assignment, we manage to construct the cluster labels directly from original samples using the binary strategy, not only preserving the data diversity but avoiding variance. Experiments on multiple publicly available datasets confirm the effectiveness of proposed DTP-SF-BVF method.

Reasoning paths are reliable information in knowledge graph completion (KGC) in which algorithms can find strong clues of the actual relation between entities. However, in real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities. According to our observation, the prediction accuracy drops significantly when paths are absent. To make the proposed algorithm more stable against the missing path circumstances, we introduce soft reasoning paths. Concretely, a specific learnable latent path embedding is concatenated to each relation to help better model the characteristics of the corresponding paths. The combination of the relation and the corresponding learnable embedding is termed a soft path in our paper. By aligning the soft paths with the reasoning paths, a learnable embedding is guided to learn a generalized path representation of the corresponding relation. In addition, we introduce a hierarchical ranking strategy to make full use of information about the entity, relation, path, and soft path to help improve both the efficiency and accuracy of the model. Extensive experimental results illustrate that our algorithm outperforms the compared state-of-the-art algorithms by a notable margin. Our code will be released at https://github.com/7HHHHH/SRP-KGC.

Few-shot knowledge graph reasoning (FS-KGR) try to infer missing facts in a knowledge graphs using limited data (such as only 3/5 samples).Existing strategies have shown good performance by mining more supervised information for few-shot learning through meta-learning and self-supervised learning. However, the problem of insufficient samples has not been fundamentally solved. In this paper, we propose a novel algorithm based on adversarial learning for Enhancing Negative samples in few-shot scenarios of FS-KGR, termed FS-KEN. Specifically, we are the first to use GAN to conduct data augmentation on FS-KGR scenario. FS-KEN uses policy gradient GANs for negative sample augmentation, solving the gradient back-propagation issue in traditional GANs. The generator aims to produce high-quality negative entities. while the objective of the discriminator is to distinguish between generated entities and real entities. Comprehensive experiments conducted on two few-shot knowledge graph completion datasets reveal that FS-KEN surpasses other baseline models, achieving state-of-the-art results.

Incomplete Multi-View Clustering (IMVC) aims to explore comprehensive representations from multiple views with missing samples. Recent studies have revealed that IMVC methods benefit from Graph Convolutional Network (GCN) in achieving robust feature imputation and effective representation learning. Despite these notable improvements, GCN imputation methods often cause a distribution shift between the imputed and original representations, particularly when the neighbors of the imputed nodes are assigned to different groups. Moreover, GCN learning methods tend to produce homogeneous imputed representations, which blur cluster boundaries and hinder effective discriminative clustering. To remedy these challenges, the Local Refinement and Global Realignment (LRGR) Self-supervised model is proposed for incomplete multi-view clustering, which includes two stages. In the first stage, a local imputed refinement module is designed to enhance the versatility of imputed representations through cross-view contrastive learning guided by view-specific prototypes. In the second stage, a global realignment module is introduced to achieve semantic consistency across views, alleviating distribution shifts by leveraging pseudo-labels and their corresponding confidence scores as guidance. Experiments on five widely used multi-view datasets demonstrate the competitiveness and superiority of our method compared to state-of-the-art approaches.

Spatial transcriptomics, comprising spatial location and high-throughput gene expression information, provides revolutionary insights into disease discovery and cellular evolution. Spatial transcriptomic clustering, which pinpoints distinct spatial domains within tissues, reveals cellular interactions and enhances our understanding of the intricate architecture of tissues. Existing methods typically construct spatial graphs using a static radius based on spatial coordinates, which hinders the accurate identification of spatial domains and complicates the precise partitioning of boundary nodes within clusters. To address this issue, we introduce a novel spatially resolved transcriptomics data clustering network (TSstc). Specifically, we employ a tailored spatial-scale modulation approach, constructing different spatial graphs incrementally as the radius of the spatial domain expands, and a Spatiality-Aware Sampling (SAS) strategy is proposed to aggregate node representations by considering the spatial dependencies between spots. We then use GCN encoders to learn gene embedding with gene graph and multiple spatial embeddings with spatial graphs. During training, we incorporate cross-view correlation-based tailored spatial regularization constraints to preserve high-quality neighbor relationships across spatial embeddings at different scales. Finally, a zero-inflated negative binomial model is utilized to capture the global probability distribution of gene expression profiles. Extensive experimental results demonstrate that our approach surpasses existing state-of-the-art methods in clustering tasks and related downstream applications.

Partially view-aligned clustering (PVC) has emerged as a critical area in multi-view clustering, addressing the inherent instance misalignment across views during data collection. The primary challenge of PVC is accurately establishing correspondences between cross-view samples. The Banzhaf index in cooperative game theory serves as an effective tool for modeling complex relationships between multi-view samples by quantifying the marginal contributions of coalition members to collaborative benefits. To this end, we propose a Banzhaf Index-driven cross-view aligNment method, dubbed BIN, which systematically evaluates each view sample's contribution to joint decision-making within a game-theoretic framework. This approach overcomes the limitations of existing PVC methods reliant on prior alignment information and enhances the robustness of multi-view matching. Specifically, we model multi-view samples as players in a cooperative game and quantify their interactions using a payoff model. Simultaneously, we propose a dual-loss constraint: (1) Banzhaf gain loss, which dynamically captures the marginal contribution of key cross-view sample pairs to reinforce associations; (2) contrast loss, which applies exclusion constraints in the feature space to suppress interference from weakly correlated samples. Together, these losses form an effective optimization mechanism. This game-theoretic approach adaptively learns sample correspondences without pre-alignment and ensures robust matching in complex misalignment scenarios. Extensive experiments demonstrate that our method achieves competitive performance against eight state-of-the-art PVC algorithms.

The exponential growth of video content necessitates efficient summarization techniques that balance local redundancy reduction and global dependency modeling. In this work, we introduce VSumMamba, an innovative video summarization approach that leverages Selective State Space Models to address the quadratic complexity limitations of Transformer based approaches meanwhile surpassing CNNs' restricted long-range modeling capabilities. The proposed framework comprises three core components: 1) a Multi-Scale Aggregator, 2) a Cascaded Temporal Modeling Module with bi-directional Mamba blocks for temporal representation enhancement, and 3) a Parallel Spatial Modeling Module employing spatial Mamba blocks, operating in concert to effectively refine spatiotemporal video representations. Through three specialized multi-scale spatial-temporal modeling schemes, VSumMamba demonstrate the ability to balance computational efficiency and summarization performance. Comprehensive evaluations on benchmarks datasets demonstrate VSumMamba's superior performance, achieving 67.5% and 56.0% F1-scores on TVSum and SumMe respectively, while maintaining lower computational cost compared to existing state-of-the-art methods.

Multi-view clustering (MVC) for remote sensing data has attracted increasing attention due to its ability to exploit complementary information from multiple modalities without requiring labels. Recent graph-based deep clustering methods have shown strong potential in modeling spatial structures inherent in remote sensing data. However, existing approaches often emphasize capturing rich node relations while overlooking the optimization of these relations, leading to noisy connections and weak inter-cluster discrimination. To address this issue, we propose a novel Multi-view Graph Clustering with dual Relation Optimization (MDRO) framework tailored for remote sensing data. Specifically, we first segment the remote sensing image into irregular superpixels to reduce computational complexity and use superpixels as graph nodes. Then, MDRO constructs high-order similarity matrices guided by clustering distribution matrices and performs dual relation optimization to suppress noise relations and strengthen similarity relations. Furthermore, an optimal transportation-based constraint is introduced to guide the formation of robust and balanced cluster assignments, mitigating over-smoothing and trivial solutions in graph learning. Comprehensive experiments on four benchmark remote sensing datasets demonstrate that MDRO consistently outperforms existing single-view and multi-view clustering methods, achieving superior accuracy and robustness.

Deep graph clustering (DGC) for attribute-missing graphs is an unsupervised task aimed at partitioning nodes with incomplete attributes into distinct clusters. Existing imputation methods for attribute-missing graphs often fail to account for the varying amounts of information available across node neighborhoods, leading to unreliable results. To address this issue, we propose a novel method named Divide-Then-Rule Graph Completion (DTRGC). This method first addresses nodes with sufficient known neighborhood information and treats the imputed results as new knowledge to iteratively impute more challenging nodes, while leveraging clustering information to correct imputation errors. Specifically, Dynamic Cluster-Aware Feature Propagation initializes missing node attributes by adjusting propagation weights based on the clustering structure. Subsequently, Hierarchical Neighborhood-Aware Imputation categorizes attribute-missing nodes into three groups based on the completeness of their neighborhood attributes. The imputation is performed hierarchically, prioritizing the groups with nodes that have the most available neighborhood information. The cluster structure is then used to refine the imputation and correct potential errors. Finally, Hop-wise Representation Enhancement integrates information across multiple hops, thereby enriching the expressiveness of node representations. Experimental results on 6 widely used graph datasets show that DTRGC significantly improves the clustering performance of various DGC methods under attribute-missing graphs.

AudioSet is a widely used benchmark in the audio research community and has significantly advanced various audio-related tasks. However, persistent issues with label accuracy and completeness remain critical bottlenecks that limit performance in downstream applications. To address the aforementioned challenges, we propose a three-stage reannotation framework that harnesses general-purpose audio-language foundation models to systematically improve the label quality of AudioSet. The framework employs a cross-modal prompting strategy, inspired by the concept of prompt chaining, wherein prompts are sequentially composed to execute subtasks (audio comprehension, label synthesis, and semantic alignment). Leveraging this framework, we construct a high-quality, structured relabeled version of AudioSet-R. Extensive experiments conducted on representative audio classification models-including AST, PANNs, SSAST, and AudioMAE-consistently demonstrate substantial performance improvements, thereby validating the generalizability and effectiveness of the proposed approach in enhancing label reliability.The code is publicly available at: https://github.com/colaudiolab/AudioSet-R.

In multi-view clustering (MVC), anchor technique is generally hailed as an effective means for filtering noise and improving computation efficiency. However, existing methods usually construct anchors via heuristic strategy, random sampling, or orthogonal learning, which overlook the distribution differences between anchors and original data, leading to anchors lacking structural characteristics. To generate the anchors that are with similar distributions to original data, in the paper we carefully devise a LASD algorithm from the perspective of optimal transport (OT). Concretely, we firstly design a Multi-View OT (MVOT) framework through complementary and consensus representation learning. Then, we theoretically demonstrate the convexity of MVOT using the positive semidefiniteness of its Hessian matrix, and accordingly the global optimal solution of each transport plan can be reached. Further, we establish the strong dual condition for MVOT by the relative interior. Based on dual programming, consequently, we successfully obtain the transport plan between anchors and original data for each view within linear computational complexity. Afterwards, the spectral clustering operation is employed on the consensus plan to produce the discrete cluster labels. Abundant experiments underscore that our learned anchors do well reflect the distributions of original data, and the generated clustering results outperform multiple strong MVC competitors, even under large-scale scenarios. The source code is available at https://github.com/junpuzhang/LASD.

Multi-view clustering aims to effectively integrate data from multiple views to uncover the underlying clustering structure. However, existing methods typically adopt direct fusion strategies for multiview data, neglecting the issues of view gap-induced heterogeneity and the imbalance in view quality. Particularly, when there are significant differences between views, such direct fusion often leads to the loss of critical information and a decline in clustering performance. To address these challenges, we propose a novel Dynamic Progressive Fusion Multi-View Clustering (DPFMVC). DPFMVC employs a view-adaptive fusion mechanism that dynamically selects the most similar views, reducing conflicts between views while preserving complementary information. Additionally, DPFMVC introduces a dual contrastive loss module and a progressive fusion loss, which effectively align sample features with clustering centers, promoting efficient integration of multi-view information. Specifically, the dual contrastive loss compares the similarity between sample features and cluster centers, ensuring cross-view feature consistency and thus enhancing the discriminability of clustering. Meanwhile, the progressive fusion loss progressively adjusts the fusion order of views, effectively reducing the negative impact of low-quality views on the clustering results, strengthening the synergy between views, and facilitating more effective information fusion.Comprehensive experiments on multiple public benchmarks show that DPFMVC delivers superior clustering results and exhibits overall great effectiveness compared to state-of-the-art techniques.

Spatial transcriptomics technologies enable the integration of gene expression profiles with spatial context, facilitating a deeper understanding of tissue architecture through downstream tasks such as clustering. However, existing approaches predominantly focus on highly variable genes (HVGs), while the informative structural and contextual signals embedded in low variability genes (LVGs) remain largely underutilized. To bridge this gap, we propose SALVG (Spatial Augmentation via Latent Variable Genes), a novel and plug-and-play framework that leverages LVG-derived structural priors to enhance HVG representation learning for spatial clustering. Specifically, SALVG constructs spatial, feature, and combined graphs for both HVGs and LVGs, and introduces two graph-based augmentation strategies to inject LVG information into HVG graphs. The first strategy enhances the HVG combined graph directly using the LVG combined graph, while the other individually augments HVG spatial and feature graphs with their LVG counterparts before fusing them into a new combined representation. These enhanced graph structures are subsequently employed for downstream clustering. To the best of our knowledge, SALVG is the first framework to exploit LVG signals for assisting HVG-centric spatial transcriptomics clustering, effectively capturing complementary structural and contextual cues. Experiments on multiple benchmarks demonstrate its effectiveness, robustness, and transferability. Case studies further confirm that LVG-derived structure enhances biological interpretability by revealing coherent spatial and cellular patterns.

Incomplete multi-view deep clustering is an emerging research hot-pot to incorporate data information of multiple sources or modalities when parts of them are missing. Most of existing approaches encode the available data observations into multiple view-specific latent representations and subsequently integrate them for the next clustering task. However, they ignore that the latent representations are unique to a fixed set of data samples in all views. Meanwhile, the pair-wise similarities of missing data observations are also failed to utilize in latent representation learning sufficiently, leading to unsatisfactory clustering performance. To address these issues, we propose an incomplete multi-view deep clustering method with data imputation and alignment. Assuming that each data sample corresponds to a same latent representation among all views, it projects the latent representations into feature spaces with neural networks. As a result, not only the available data observations are reconstructed, but also the missing ones can be imputed accordingly. Moreover, a linear alignment measurement of linear complexity is defined to compute the pair-wise similarities of all data observations, especially including those of the missing. By executing the above two procedures iteratively, the discriminative latent representations can be learned and used to group the data into categories with off-the-shelf clustering algorithms. In experiment, the proposed method is validated on a set of benchmark datasets and achieves state-of-the-art performances.

Existing multi-view clustering methods employ various strategies to address data-level sparsity and view-level dynamic fusion. However, we identify a critical yet overlooked issue: varying sparsity across views. Cross-view sparsity variations lead to encoding discrepancies, heightening sample-level semantic heterogeneity and making view-level dynamic weighting inappropriate. To tackle these challenges, we propose Adaptive Sparse Autoencoders for Multi-View Clustering (SparseMVC), a framework with three key modules. Initially, the sparse autoencoder probes the sparsity of each view and adaptively adjusts encoding formats via an entropy-matching loss term, mitigating cross-view inconsistencies. Subsequently, the correlation-informed sample reweighting module employs attention mechanisms to assign weights by capturing correlations between early-fused global and view-specific features, reducing encoding discrepancies and balancing contributions. Furthermore, the cross-view distribution alignment module aligns feature distributions during the late fusion stage, accommodating datasets with an arbitrary number of views. Extensive experiments demonstrate that SparseMVC achieves state-of-the-art clustering performance. Our framework advances the field by extending sparsity handling from the data-level to view-level and mitigating the adverse effects of encoding discrepancies through sample-level dynamic weighting. The source code is publicly available at https://github.com/cleste-pome/SparseMVC.

Most existing multi-view clustering methods aim to generate a consensus partition across all views, based on the assumption that all views share the same sample arrangement. However, in real-world scenarios, the collected data across different views is often unsynchronized, making it difficult to ensure consistent sample correspondence between views. To address this issue, we propose a scalable sample-alignment-based multi-view clustering method, referred to as SSA-MVC. Specifically, we first employ a cluster-label matching (CLM) algorithm to select the view whose clustering labels best match those of the others as the benchmark view. Then, for each of the remaining views, we construct representations of non-aligned samples by computing their similarities with aligned samples. Based on these representations, we build a similarity graph between the non-aligned samples of each view and those in the benchmark view, which serves as the alignment criterion. This alignment criterion is then integrated into a late-fusion framework to enable clustering without requiring aligned samples. Notably, the learned sample alignment matrix can be used to enhance existing multi-view clustering methods in scenarios where sample correspondence is unavailable. The effectiveness of the proposed SSA-MVC algorithm is validated through extensive experiments conducted on eight real-world multi-view datasets.

Deep graph clustering (DGC) aims to partition graph nodes into distinct clusters in an unsupervised manner. Despite rapid advancements in this field, DGC remains inherently challenging due to the absence of ground-truth, which complicates the design of effective algorithms and impedes the establishment of standardized benchmarks. The lack of unified datasets, evaluation protocols, and metrics further exacerbates these challenges, making it difficult to systematically assess and compare DGC methods. To address these limitations, we introduce $\texttt{DGCBench}$, the first comprehensive and unified benchmark for DGC methods. It evaluates 12 state-of-the-art DGC methods across 12 datasets from diverse domains and scales, spanning 6 critical dimensions: $\textbf{discriminability}$, $\textbf{effectiveness}$, $\textbf{scalability}$, $\textbf{efficiency}$, $\textbf{stability}$, and $\textbf{robustness}$. Additionally, we develop $\texttt{PyDGC}$, an open-source Python library that standardizes the DGC training and evaluation paradigm. Through systematic experiments, we reveal persistent limitations in existing methods, specifically regarding the homophily bottleneck, training instability, vulnerability to perturbations, efficiency plateau, scalability challenges, and poor discriminability, thereby offering actionable insights for future research. We hope that $\texttt{DGCBench}$, $\texttt{PyDGC}$, and our analyses will collectively accelerate the progress in the DGC community. The code is available at https://github.com/Marigoldwu/PyDGC.

Although receiving notable improvements, current multi-view clustering (MVC) techniques generally rely on feature library mechanisms to propagate accumulated knowledge from historical views to newly-arrived data, which overlooks the information pertaining to basis embedding within each view. Moreover, the mapping paradigm inevitably alters the values of learned landmarks and built affinities due to the uninterruption nature, accordingly disarraying the hierarchical cluster structures. To mitigate these two issues, we in the paper provide a named BSTM algorithm. Concretely, we firstly synchronize with the distinct dimensions by introducing a group of specialized projectors, and then establish unified anchors for all views collected so far to capture intrinsic patterns. Afterwards, departing from per-view architectures, we devise a shared bipartite graph construction via indicators to quantify similarity, which not only avoids redundant data-recalculations but alleviates the representation distortion caused by fusion. Crucially, there two components are optimized within an integrated framework, and collectively facilitate knowledge transfer upon encountering incoming views. Subsequently, to flexibly do transformation on anchors and meanwhile maintain numerical consistency, we develop a bit-swapping scheme operating exclusively on 0 and 1. It harmonizes anchors on current view and that on previous views through one-hot encoded row and column attributes, and the graph structures are correspondingly reordered to reach a matched configuration. Furthermore, a computationally efficient four-step updating strategy with linear complexity is designed to minimize the associated loss. Extensive experiments organized on publicly-available benchmark datasets with varying missing percentages confirm the superior effectiveness of our BSTM.

With the increasing adoption of Retrieval-Augmented Generation (RAG) systems for knowledge-intensive tasks, ensuring the adequacy of retrieved documents has become critically important for generation quality. Traditional reranking approaches face three significant challenges: substantial computational overhead that scales with document length, dependency on plain text that limits application in sensitive scenarios, and insufficient assessment of document value beyond simple relevance metrics. We propose EAReranker, an efficient embedding-based adequacy assessment framework that evaluates document utility for RAG systems without requiring access to original text content. The framework quantifies document adequacy through a comprehensive scoring methodology considering verifiability, coverage, completeness and structural aspects, providing interpretable adequacy classifications for downstream applications. EAReranker employs a Decoder-Only Transformer architecture that introduces embedding dimension expansion method and bin-aware weighted loss, designed specifically to predict adequacy directly from embedding vectors. Our comprehensive evaluation across four public benchmarks demonstrates that EAReranker achieves competitive performance with state-of-the-art plaintext rerankers while maintaining constant memory usage ($\sim$550MB) regardless of input length and processing 2-3x faster than traditional approaches. The semantic bin adequacy prediction accuracy of 92.85\% LACC@10 and 86.12\% LACC@25 demonstrates its capability to effectively filter out inadequate documents that could potentially mislead or adversely impact RAG system performance, thereby ensuring only high-utility information serves as generation context. These results establish EAReranker as an efficient and practical solution for enhancing RAG system performance through improved context selection while addressing the computational and privacy challenges of existing methods.

Spatial transcriptomics (ST) technologies provide gene expression measurements with spatial resolution, enabling the dissection of tissue structure and function. A fundamental challenge in ST analysis is clustering spatial spots into coherent functional regions. While existing models effectively integrate expression and spatial signals, they largely overlook sequence-level biological priors encoded in the DNA sequences of expressed genes. To bridge this gap, we propose SAINT (Sequence-Aware Integration for Nucleotide-informed Transcriptomics), a unified framework that augments spatial representation learning with nucleotide-derived features. We construct sequence-augmented datasets across 14 tissue sections from three widely used ST benchmarks (DLPFC, HBC, and MBA), retrieving reference DNA sequences for each expressed gene and encoding them using a pretrained Nucleotide Transformer. For each spot, gene-level embeddings are aggregated via expression-weighted and attention-based pooling, then fused with spatial-expression representations through a late fusion module. Extensive experiments demonstrate that SAINT consistently improves clustering performance across multiple datasets. Experiments validate the superiority, effectiveness, sensitivity, and transferability of our framework, confirming the complementary value of incorporating sequence-level priors into spatial transcriptomics clustering.

Abstract Clustering ensemble, which aims to learn a robust consensus clustering from multiple weak base clusterings, has achieved promising performance on various applications. With the development of big data, the scale and complexity of data is constantly increasing. However, most existing clustering ensemble methods typically employ shallow clustering algorithms to generate base clusterings. When confronted with high-dimensional complex data, these shallow algorithms fail to fully utilize the intricate features present in the latent data space. As a result, the quality and diversity of the generated base clusterings are insufficient, thus affecting the subsequent ensemble performance. To address this issue, we propose a novel clustering ensemble algorithm for handling deep embeddings using cluster confidence (CEDECC) to improve the robustness and performance. Instead of simply combining deep clustering with clustering ensembles, we take into consideration that the performance of existing deep clustering methods heavily relies on the quality of low-dimensional embeddings generated during the pre-training stage. The quality of embeddings is unstable due to the influence of different initialization parameters. In CEDECC, specifically, we first construct a cluster confidence measure to evaluate the quality of low-dimensional embeddings. Typically, high-quality low-dimensional embeddings yield accurate clustering results with the same model parameters. Then, we utilize multiple high-quality embeddings to generate the base partitions. In the ensemble strategy phase, we consider the cluster-wise diversity and propose a novel ensemble cluster estimation to improve the overall consensus performance of the model. Extensive experiments on three benchmark datasets and four real-world biological datasets have demonstrated that the proposed CEDECC consistently outperforms the state-of-the-art clustering ensemble methods.

Repetitive Negative Sequential Patterns (RNSPs) can provide critical insights into the importance of sequences. However, most current RNSP mining methods require users to set an appropriate support threshold to obtain the expected number of patterns, which is a very difficult task for the users without prior experience . To address this issue, we propose a new algorithm, TK-RNSP, to mine the Top- K RNSPs with the highest support, without the need to set a support threshold. In detail, we achieve a significant breakthrough by proposing a series of definitions that enable RNSP mining to satisfy anti-monotonicity. Then, we propose a bitmap-based Depth-First Backtracking Search (DFBS) strategy to decrease the heavy computational burden by increasing the speed of support calculation. Finally, we propose the algorithm TK-RNSP in an one-stage process, which can effectively reduce the generation of unnecessary patterns and improve computational efficiency comparing to those two-stage process algorithms. To the best of our knowledge, TK-RNSP is the first algorithm to mine Top- K RNSPs. Extensive experiments on eight datasets show that TK-RNSP has better flexibility and efficiency to mine Top- K RNSPs.

Gradient clipping has long been considered essential for ensuring the convergence of Stochastic Gradient Descent (SGD) in the presence of heavy-tailed gradient noise. In this paper, we revisit this belief and explore whether gradient normalization can serve as an effective alternative or complement. We prove that, under individual smoothness assumptions, gradient normalization alone is sufficient to guarantee convergence of the nonconvex SGD. Moreover, when combined with clipping, it yields far better rates of convergence under more challenging noise distributions. We provide a unifying theory describing normalization-only, clipping-only, and combined approaches. Moving forward, we investigate existing variance-reduced algorithms, establishing that, in such a setting, normalization alone is sufficient for convergence. Finally, we present an accelerated variant that under second-order smoothness improves convergence. Our results provide theoretical insights and practical guidance for using normalization and clipping in nonconvex optimization with heavy-tailed noise.

Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8% of the parameters required by leading methods.

Multi-view bipartite graph clustering (MVBGC) is an active pipeline in unsupervised learning to tackle the limited scalability issue of traditional graph clustering. Despite improved performance, numerous variants still fall under conventional modeling that plugs additional modules, which however induces increasingly intricate models and fails to reveal the inherent variable relationship. We make the first attempt to introduce probabilistic graphical models for modeling the multi-view bipartite graph clustering task, reformulating it as a maximum likelihood estimation (MLE) problem. Such a setting uncovers the underlying probabilistic correlations among the commonality, view-specific variables, and noisy components. By pruning redundancy and disturbance collectively referred to as noise, we prove that minimizing the total noise is an approximation of the lower bound of MLE for multi-view data observations. We further generalize the MLE setting with clustering-suited constraints, deriving a Generalized Probabilistic Graphical Modeling framework (GProM), achieving an interpretable, concise, and flexible MVBGC framework. Extensive experiments verify the effectiveness of our framework. Furthermore, statistical significance analysis reveals the effectiveness of different distribution assumptions, providing valuable insights for model design.

Multi-view clustering (MVC) is a fast-growing research direction. However, most existing MVC works focus on concrete objects (e.g., cats, desks) but ignore abstract objects (e.g., knowledge, thoughts), which are also important parts of our daily lives and more correlated to cognition. Relational knowledge, as a typical abstract concept, describes the relationship between entities. For example, "Cats like eating fishes," as relational knowledge, reveals the relationship "eating" between "cats" and "fishes." To fill this gap, we first point out that MVC on relational knowledge is considered an important scenario. Then, we construct 8 new datasets to lay research grounds for them. Moreover, a simple yet effective relational knowledge MVC paradigm (RK-MVC) is proposed by compensating the omitted sample-global correlations from the structural knowledge information. Concretely, the basic consensus features are first learned via adopted MVC backbones, and sample-global correlations are generated in both coarse-grained and fine-grained manners. In particular, the sample-global correlation learning module can be easily extended to various MVC backbones. Finally, both basic consensus features and sample-global correlation features are weighted fused as the target consensus feature. We adopt 9 typical MVC backbones in this paper for comparison from 7 aspects, demonstrating the promising capacity of our RK-MVC.

Temporal Graph Clustering (TGC) is a new task with little attention, focusing on node clustering in temporal graphs. Compared with existing static graph clustering, it can find the balance between time requirement and space requirement (Time-Space Balance) through the interaction sequence-based batch-processing pattern. However, there are two major challenges that hinder the development of TGC, i.e., inapplicable clustering techniques and inapplicable datasets. To address these challenges, we propose a comprehensive benchmark, called BenchTGC. Specially, we design a BenchTGC Framework to illustrate the paradigm of temporal graph clustering and improve existing clustering techniques to fit temporal graphs. In addition, we also discuss problems with public temporal graph datasets and develop multiple datasets suitable for TGC task, called BenchTGC Datasets. According to extensive experiments, we not only verify the advantages of BenchTGC, but also demonstrate the necessity and importance of TGC task. We wish to point out that the dynamically changing and complex scenarios in real world are the foundation of temporal graph clustering.

Simple multiple kernel k-means (SMKKM) introduces a new minimization-maximization learning paradigm for multi-view clustering and makes remarkable achievements in some applications. As one of its variants, localized SMKKM (LSMKKM) is recently proposed to capture the variation among samples, focusing on reliable pairwise samples, which should keep together and cut off unreliable, farther pairwise ones. Though demonstrating effectiveness, we observe that LSMKKM indiscriminately utilizes the variation of each sample, resulting in unsatisfying clustering performance. To overcome this limitation, we propose a sample adaptive localized SMKKM (SAL-SMKKM) algorithm where the weight of the local alignment for each sample can be adaptively adjusted, resulting in a more challenging tri-level minimization-minimization-maximization. To deal with it, we reformulate it into a minimization problem of an optimal function characterized by minimization-maximization dynamics, prove its differentiability, and develop a reduced gradient descent method to optimize it. We then theoretically analyze the clustering performance of the proposed SAL-SMKKM by deriving its generalization error bound. In addition, we empirically evaluate the clustering performance of the proposed SAL-SMKKM on several benchmark datasets. Experiment results clearly indicate that proposed algorithms consistently outperform state-of-the-art ones. Finally, we apply the proposed SAL-SMKKM to the multi-modal parcellation of the human cerebral cortex, which is essential and helpful to understanding brain organization and function. As seen, SAL-SMKKM achieves accurate parcellation in an automatic and objective manner without any manual intervention, which once again demonstrates its validity and effectiveness in practical applications.

The bounded variance, gradient Lipschitz, and unbiased stochastic gradient are three key assumptions for ensuring the convergence and generalization of stochastic methods, especially in nonconvex scenarios. However, it is important to acknowledge that in practical applications, one or more of these assumptions might be violated, which is the main focus of this paper. In this study, we aim to demonstrate that by incorporating simple gradient normalization with momentum, SGD can effectively guarantee convergence and generalization, even in the presence of unbounded noise, weak gradient Lipschitz, and biased stochastic gradient caused by delays. These results significantly broaden the range of applications for stochastic algorithms, as they relax the previous assumptions and provide more flexibility in real-world scenarios.

Attribute-missing graph learning, a common yet challenging problem, has recently attracted considerable attention. Existing efforts have at least one of the following limitations: 1) lack a noise filtering and information enhancing scheme, resulting in less comprehensive data completion; 2) isolate the node attribute and graph structure encoding processes, introducing more parameters and failing to take full advantage of the two types of information; and 3) impose overly strict distribution assumptions on the latent variables, leading to biased or less discriminative node representations. To tackle the issues, based on the idea of introducing intimate information interaction between the two information sources, we propose Weight-sharing Attribute-missing Graph autoEncoder (WAGE) to boost the expressive capacity of node representations for high-quality missing attribute reconstruction. Specifically, three strategies have been conducted. Firstly, we entangle the attribute embedding and structure embedding by introducing a weight-sharing architecture to share the parameters learned by both processes, which allows the network training to benefit from more abundant and diverse information. Secondly, we introduce a $K$K-nearest neighbor-based dual non-local learning mechanism to improve the quality of data imputation by revealing unobserved high-confidence connections while filtering unreliable ones. Thirdly, we manually mask the connections on multiple adjacency matrices and force the structure-oriented embedding sub-network to recover the actual adjacency matrix, thus enforcing the resulting network to be able to selectively exploit more high-order discriminative features for data completion. Extensive experiments on six benchmark datasets demonstrate the effectiveness and superiority of WAGE against state-of-the-art competitors.

We introduce WildVideo, an open-world benchmark dataset designed to address how to assess hallucination of Large Multi-modal Models (LMMs) for understanding video-language interaction in the wild. Our WildVideo comprehensively tests the perceptual, cognitive, and contextual comprehension hallucination of LMMs through both single-turn and multi-turn open-ended question-answering (QA) tasks on videos captured from two human perspectives (i.e. first-person view and third-person view). We define 9 distinct tasks that challenge LMMs across multi-level perceptual tasks (e.g., static and dynamic perception), multi-aspect cognitive tasks (e.g., commonsense, world knowledge), and multi-faceted contextual comprehension tasks (e.g., contextual ellipsis, cross-turn retrieval). The benchmark consists of 1,318 meticulously curated videos, supplemented with 13,704 single-turn QA pairs and 1,585 multi-turn dialogues (up to 5 turns). We evaluated 14 commonly-used LMMs on WildVideo, revealing significant hallucination issues of current LMMs, highlighting substantial gaps in their current capabilities.

Graph classification has been a prominent problem in graph machine learning fields. This problem has been investigated by leveraging message passing neural networks (MPNNs) to learn powerful graph representations. However, MPNNs extract topological semantics implicitly under label supervision, which could suffer from domain shift and label scarcity in unsupervised domain adaptation settings. In this paper, we propose an effective solution named Dual Variational Semantics Graph Mining (DREAM) for unsupervised graph domain adaptation by combining graph structural semantics from complementary perspectives. Besides a message passing branch to learn implicit semantics, our DREAM trains a path aggregation branch, which can provide explicit high-order structural semantics as a supplement. To train these two branches conjointly, we employ an expectation-maximization (EM) style variational framework for the maximization of likelihood. In the E-step, we fix the message passing branch and construct a graph-of-graph to indicate the geometric correlation between source and target domains, which would be adopted for the optimization of the other branch. In the M-step, we train the message passing branch and update the graph neural networks on the graph-of-graph with the other branch fixed. The alternative optimization improves the collaboration of knowledge from two branches. Extensive experiments on several benchmark datasets validate the superiority of the proposed DREAM compared with various baselines.

Although data-driven methods usually have noticeable performance on disease diagnosis and treatment, they are suspected of leakage of privacy due to collecting data for model training. Recently, federated learning provides a secure and trustable alternative to collaboratively train model without any exchange of medical data among multiple institutes. Therefore, it has draw much attention due to its natural merit on privacy protection. However, when heterogenous medical data exists between different hospitals, federated learning usually has to face with degradation of performance. In the paper, we propose a new personalized framework of federated learning to handle the problem. It successfully yields personalized models based on awareness of similarity between local data, and achieves better tradeoff between generalization and personalization than existing methods. After that, we further design a differentially sparse regularizer to improve communication efficiency during procedure of model training. Additionally, we propose an effective method to reduce the computational cost, which improves computation efficiency significantly. Furthermore, we collect five real medical datasets, including two public medical image datasets and three private multi-center clinical diagnosis datasets, and evaluate its performance by conducting nodule classification, tumor segmentation, and clinical risk prediction tasks. Comparing with 14 existing related methods, the proposed method successfully achieves the best model performance, and meanwhile up to 60% improvement of communication efficiency.

Clustering ensemble has been widely studied in data mining and machine learning. However, the existing clustering ensemble methods do not pay attention to fairness, which is important in real-world applications, especially in applications involving humans. To address this issue, this paper proposes a novel fair clustering ensemble method, which takes multiple base clustering results as inputs and learns a fair consensus clustering result. When designing the algorithm, we observe that one of the widely used definitions of fairness may cause a cluster imbalance problem. To tackle this problem, we give a new definition of fairness that can simultaneously characterize fairness and cluster capacity equality. Based on this new definition, we design an extremely simple yet effective regularized term to achieve fairness and cluster capacity equality. We plug this regularized term into our clustering ensemble framework, finally leading to our new fair clustering ensemble method. The extensive experiments show that, compared with the state-of-the-art clustering ensemble methods, our method can not only achieve a comparable or even better clustering performance, but also obtain a much fairer and better capacity equality result, which well demonstrates the effectiveness and superiority of our method.

The rapid advancement of single-cell sequencing technology has generated vast amounts of multi-omics data, presenting unprecedented opportunities for single-cell multi-omics clustering analysis. However, existing single-cell clustering algorithms focus on extracting shared representations, overlooking the interactions and correlations among cells. This oversight inevitably leads to biased or confounded cell clustering results. In this paper, we propose a cell similarity purified adaptive fusion network for single-cell multi-omics clustering, named scSPAF, which adopts a multi-level fusion approach to thoroughly explore the consistency and complementarity of omics data. Specifically, we design a cell similarity purification module to accurately incorporate neighborhood information among cells into cell features, thereby purifying the latent representation that reflects cell correlations. In addition, we align attribute features from different omics to extract the consistent representation across omics. Simultaneously, by employing an adaptive fusion mechanism, we integrate representations of omics-specific and the consistent representation across omics to generate more discriminative representations of omics, further enhancing the clustering performance. Experimental results obtained from six real-world datasets demonstrate the superiority of the scSPAF algorithm when compared with other state-of-the-art methods.

Hyperspectral band selection, aimed at identifying key spectral bands from the original image, is crucial for reducing dimensionality and enhancing computational efficiency in hyperspectral image (HSI) analysis. Graph learning-based methods have attracted considerable attention due to their efficiency in representing structural correlations between bands and their powerful capability to extract features. However, existing methods have limitations in utilizing spatial relationships among bands and learning their discriminative characteristics. To address these limitations, we propose a Diversity Learning Guided Dual Graph Autoencoder (DLG-DGAE) for unsupervised hyperspectral band selection. In our framework, we integrate a Dual Graph Autoencoder (DGAE) module designed to extract information from both the spatial and spectral relationships among bands, thus fully capturing the structural similarity of the bands. Additionally, we introduce a Spectral Diversity Learning (SDL) strategy to reduce redundant information in the latent representation and enhance the discriminative properties of each band. In the final step, we proceed to cluster the fused latent embeddings. Within each cluster, we select the band exhibiting the highest information entropy as the representative band. Through extensive experimentation on three publicly available datasets, our results consistently indicate that the proposed method surpasses other state-of-the-art techniques. The code is available athttps://github.com/fengwe1/DLG-DGAE.

Remote-sensing fine-grained ship classification (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data, limiting the effectiveness of traditional supervised classification methods. Recent advancements in large pretrained vision-language models (VLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning, particularly in understanding image content. This study delves into harnessing the potential of VLMs to enhance classification accuracy for unseen ship categories, which holds considerable significance in scenarios with restricted data due to cost or privacy constraints. Directly fine-tuning VLMs for RS-FGSC often encounters the challenge of overfitting the seen classes, resulting in suboptimal generalization to unseen classes, which highlights the difficulty in differentiating complex backgrounds and capturing distinct ship features. To address these issues, we introduce a novel prompt tuning technique that employs a hierarchical, multigranularity prompt design. Our approach integrates remote sensing ship priors through bias terms, learned from a small trainable network. This strategy enhances the model’s generalization capabilities while improving its ability to discern intricate backgrounds and learn discriminative ship features. Furthermore, we contribute to the field by introducing a comprehensive dataset, FGSCM-52, significantly expanding existing datasets with more extensive data and detailed annotations for less common ship classes. Extensive experimental evaluations demonstrate the superiority of our proposed method over current state-of-the-art techniques. The source code will be made publicly available.

Subspace clustering contributes a lot to the development of unsupervised hyperspectral image (HSI) classification task due to its ability of processing high-dimensional data. Generally, subspace clustering suffers from the bottlenecks of high computational cost when dealing with large-scale HSI. Some researches address this problem by using superpixel segmentation. However, the introduction of superpixel segmentation may cause some adverse effects, including interference from non-target region samples and the oversmoothing of superpixel-level samples. To overcome these issues, we propose a masked superpixel contrastive subspace clustering (MSCSC) for large-scale HSI classification. Specifically, we leverage hyperspectral masked autoencoder rather than conventional autoencoder as the backbone to mitigate the interference of non-target region samples during feature extraction. Then, based on this backbone, we integrate contrastive learning with self-expressiveness based subspace clustering to form the superpixel-level contrastive subspace clustering network, which aims to learn the discriminative superpixel-level self-representation. Moreover, we design a novel data augmentation strategy to ensure learn global and local information, improving the distinguishability of superpixel-level features. Experiments on four popular HSI datasets validate the superiority of our proposed method, with a large accuracy improvement compared to state-of-the-art methods.

Hyperspectral video (HSV) provides rich spectral-spatial-temporal information, enabling the capture of complex object dynamics beyond the limitations of conventional single- and multi-modal tracking. However, current HSV tracking methods face challenges such as data scarcity, band gaps, spectral fragmentation, temporal underutilization, and high computational load, which constrain performance. In this article, we present SpectralTrack, a novel HSV tracking framework with spectral-spatial fusion and memory enhancement. SpectralTrack incorporates an explicit visual prompting module to mitigate band gaps and spectral fragmentation. We further introduce an extraction-matching-interaction module, which leverages a template-bridging search adapter and a multi-layer perceptron adapter within a multi-modal Transformer architecture for efficient cross-modal feature extraction-matching-interaction. Additionally, a memory perception module enhances state reasoning by injecting temporal prompts to refine spectral and spatial cues. SpectralTrack follows parameter-efficient fine-tuning and feature-level fusion to alleviate data scarcity and reduce computational overhead. We instantiate two variants, SpectralTrack and SpectralTrack+, across nine HSV tracking datasets, demonstrating superior effectiveness over extensive trackers. Implementations and results will be available at https://github.com/YZCU/SpectralTrack.

Incomplete multi-view clustering has gained significant attention due to the prevalence of incomplete multi-view data in real-world scenarios. However, existing methods often overlook the critical role of inter-view relationships. In unsupervised settings, selectively leveraging cross-view topological relationships can effectively guide view completion and representation learning. To address this challenge, we propose a novel framework called Selective Cross-View Topology Incomplete Multi-View Clustering (SCVT). Our approach constructs a view topology graph using the Optimal Transport (OT) distance between view. This graph helps identify neighboring views for those with missing data, enabling the inference of topological relationships and accurate completion of missing samples. Additionally, we introduce the Max View Graph Contrastive Alignment module to facilitate information transfer and alignment across neighboring views. Furthermore, we propose the View Graph Weighted Intra-View Contrastive Learning module, which enhances representation learning by pulling representations of samples within the same cluster closer, while applying varying degrees of enhancement across different views based on the view graph. Our method achieves state-of-the-art performance on seven benchmark datasets, significantly outperforming existing methods for incomplete multi-view clustering and demonstrating its effectiveness.

Knowledge graphs (KGs) represent known entities and their relationships using triplets, but this method cannot represent relationships between facts, limiting their expressiveness. Recently, the Bi-level Knowledge Graph (Bi-level KG) has addressed this issue by modeling facts as nodes and establishing relationships between these facts, introducing two new tasks: triplet prediction and conditional link prediction. Existing methods enhance triplets through data augmentation method and represent facts using entity representations. However, these methods do not address the isolated nodes at the structure level, nor do they effectively capture the information of facts at the feature level. To address these two issues, we design a data augmentation method that identifies islanded node by detecting anomalous structures and features in the graph. Subsequently, we perform similar subgraph matching for each isolated node to construct potential facts. To enrich the features of facts, we design a weighted combination initialization method for facts and introduce a new relation $\widetilde {R}$ , to connect facts with related entities. This approach allows for the co-training of fact and entity representations during the training process. Extensive experiments validate the effectiveness of our data augmentation and co-training methods. Our model achieves optimal performance in triplet prediction and conditional link prediction tasks.

In recent years, multi-view unsupervised feature selection has gained significant interest for its ability to efficiently handle multi-view datasets while offering better interpretability. Existing multi-view unsupervised feature selection methods construct graphs based on the relationship between samples. In fact, in feature selection, it is more important to focus on the relationships between features. However, constructing a complete graph to capture the relationship between features would incur a space and time complexity of $O(d^{2})$ or even higher. Therefore, we introduce an anchor-based strategy and build a feature bipartite graph to reduce complexity. In addition, since existing methods cannot directly extract feature importance from a feature bipartite graph, we design an effective and low-complexity method to directly obtain feature scores from a feature bipartite graph. Compared with the feature importance extraction method based on the complete graph, our proposed method reduces the time complexity from $O(d^{3})$ to $O(d)$ . To the best of our knowledge, our proposed method is the first multi-view unsupervised feature selection algorithm that achieves $O(nd)$ space and time complexity without data segmentation. Specifically, this method adaptively learns feature-level anchor graph structures through self-expressive multi-view subspace learning, which can effectively capture the structural information between features and anchors. Meanwhile, the proposed method projects low-dimensional anchors to common dimensions and aligns them with consensus anchors to capture the consistency and complementary information between different views. The superiority of the proposed algorithm is demonstrated by comparing it with seven state-of-the-art algorithms on five public image and two biological information multi-view datasets. The code of the proposed method is publicly available at https://github.com/getupLiu/AFRC.

Multi-view Subspace Clustering (MVSC) effectively aggregating multiple data sources to promise clustering performance. Recently, various anchor-based variants have been introduced to effectively alleviate the computation complexity of MVSC. Although satisfactory advancement has been achieved, existing methods either independently learn anchor matrices and their anchor representations or learn a consensus anchor matrix and unified anchor representation, failing to capture both consistency and complementary information simultaneously. In addition, the time complexity of obtaining clustering results by applying Singular Value Decomposition (SVD) on the anchor representation matrix remains high. To tackle the above problems, we propose an Adaptive Anchor-guided Representation Learning for Efficient Multi-view Subspace Clustering (A2RL-EMVSC) framework, which integrates consensus anchors learning, anchor-guided representation learning and matrix factorization to enhance clustering performance and scalability. Technically, the proposed method learns view-specific anchor representation matrices by consensus anchors guidance, which simultaneously exploit consistency and complementary information. Moreover, by applying matrix decomposition to the view-specific anchor representation matrices, clustering results can be achieved with linear time complexity. Extensive experiments on ten challenging multi-view datasets show that the proposed method can improve the effectiveness and superiority of clustering compared with state-of-the-art methods.

Graph neural networks (GNNs) have shown remarkable success in graph-level classification tasks. However, most of the existing GNN-based studies are based on balanced datasets, while many real-world datasets exhibit long-tailed distributions. In such datasets, the tail classes receive limited attention during training, leading to prediction bias and degraded performance. To address this issue, a range of long-tailed learning strategies have been proposed, such as data re-balancing and transfer learning. However, these approaches encounter several challenges, including insufficient representation capacity for tail classes and their evaluation solely on uniform test data, limiting their capacity to handle unknown class distributions. To tackle these challenges, we introduce a novel framework, namely Knowledge-diverse Experts (KDEX) for long-tailed graph classification. Our KDEX leverages a dynamic memory module to enable the transfer of knowledge from head to tail, which improves the representation ability of the tail. To deal with unknown test distributions, KDEX introduces a knowledge-diverse expert training approach to train experts with different capacities in managing various test distributions. Moreover, we train the hierarchical router in a self-supervised manner to dynamically aggregate each knowledge-diverse expert during testing. Experimental results on multiple benchmarks reveal that our KDEX outperforms current baselines in both standard and test-agnostic long-tailed graph classification.

Inductive relation prediction aims to predict missing connections between entities unseen during training. Recent approaches adopt binary (positive or negative) training labels, which indicate whether the query relation exists between the entities, as supervision to teach models recognizing the entity-independent relation patterns in the context (enclosed subgraph or connective path). However, we argue that in this kind of method, the trained models are guided to make relation predictions by remembering whether the query relation and its contextual relational pattern co-occur more frequently in positive or negative samples. This solution could introduce two major limitations: 1) the model struggles with long-tail combinations, i.e., the combination between query relation and the relational pattern rarely occurs during training; 2) when noisy relational patterns, which fail to provide evidence for predicting the query relation, frequently occur with the query relation in positive training samples, the model will be misled into considering the noisy relational patterns as a feature supporting the existence of the query relation. To solve these problems, we propose ToC (Thinking on Context). ToC first utilizes large language models (LLMs) to incorporate a chain of thought as an additional supervisory constraint, guiding the model to make relational predictions based on logical reasoning instead of co-occurrence frequency. Additionally, ToC employs the reasoning capabilities of LLMs to construct context-level negative samples, aiding the model in identifying and disregarding noisy relational patterns. Extensive experiments show that ToC significantly outperforms state-of-the-art methods across three widely used datasets in multiple inductive settingshttps://github.com/AI-Chen/ToC_KGC.

Multi-view clustering (MVC) has demonstrated impressive performance due to its ability to capture both consistency and diversity information among views. However, most existing techniques assume that all views are available in advance, making them inadequate for stream-view data, such as in intelligent transportation systems and medical imaging analysis, where memory constraints or privacy concerns prevent storing all previous views. Although some methods attempt to address this issue by capturing consistency information, they often fail to effectively extract diversity information and cross-view relationships. We argue that these limitations are inherent to incremental multi-view clustering (IMVC), as the inability to retain all previous views inevitably leads to insufficient information utilization, thereby compromising performance. To address these challenges, we propose a novel algorithm, termed Incremental Multi-View Clustering with Cross-View Correlation and Diversity (CDIMVC). Unlike existing methods that only retain consistency information, CDIMVC also preserves diversity information and utilizes similarity matrices to capture cross-view relationships. To implement this method, we develop three key modules: the dynamic view correlation analysis module (DVCAM), the knowledge extraction module (KEM), and the knowledge transfer module (KTM). When a new data view arrives, DVCAM first assesses its importance and correlation with historical views. Subsequently, KEM computes its consistency and diversity information by comparing it to those in the knowledge base. Finally, KTM facilitates the effective transmission of past knowledge, preventing the loss of historical information. By integrating these modules, CDIMVC can effectively capture cross-view relationships and diversity information, facilitating efficient knowledge updating and maintenance. An alternating procedure is also designed to optimize the resulting optimization problem. Experimental results show that CDIMVC exceeds state-of-the-art methods, demonstrating its effectiveness in handling stream-view data.

Multi-view clustering (MVC) for remote sensing data has demonstrated significant potential in Earth observation, given its ability to aggregate multi-source information without relying on labels. Despite achieving compelling results through the combination of deep encoders and contrastive learning, existing algorithms still face two limitations: inadequate exploration of diverse spatial relationships and inability to guide the selection of sample pairs leads to blind sampling, both of which lead to suboptimal clustering performance. To tackle these challenges, we propose a sampling enhanced contrastive multi-view clustering method for remote sensing data, namely SEC-LSRM. The proposed method incorporates long- and short-range information mining to enhance clustering performance. By aggregating shortrange information extracted through autoencoders and longrange information obtained via graph autoencoders, our method improves the sampling quality of positive and negative sample pairs. To render the extracted features more compact, a multiview correlation reduction strategy is devised to filter out irrelevant information. With the extracted comprehensive features, an adaptive sampling strategy is designed to obtain high-quality positive and negative samples. Subsequently, we select positive and negative sample pairs based on these affinity matrices with idempotence and block diagonal constraints. Moreover, we integrate the optimization of these sample pairs and contrastive learning within the same framework to achieve iterative updates of both. Experiments conducted on multiple multi-view remote sensing datasets illustrate that our proposed SEC-LSRM method achieves excellent and reliable clustering performance.

Bipartite graph clustering (BGC) has emerged as a fast-growing research in the clustering community. Despite BGC has achieved promising scalability, most variants still suffer from the following concerns: a) Susceptibility to noisy features. They construct bipartite graphs in the raw feature space, inducing poor robustness to noisy features. b) Inflexible anchor selection strategies. They usually select anchors through heuristic sampling or constrained learning methods, degrading flexibility. c) Partial structure mining. Existing methods are mainly built upon Linear Reconstruction Paradigm (LRP) from subspace clustering or Locally Linear Paradigm (LLP) from manifold learning, which partially exploit linear or locally linear structures, lacking a unified perspective to integrate global complementary structures. To this end, we propose a novel model, termedJoint Robust Embedding and Structural FusionBipartiteGraphClustering (JetBGC), which focuses on three aspects, namely robustness, flexibility, and complementarity. Concretely, we first introduce a robust embedding learning module to extract latent representation that can reduce the impact of noisy features. Then, we optimize anchors via a constraint-free strategy that can flexibly capture data distribution. Furthermore, we revisit the consistency and specificity of LRP and LLP, and design a new unified structural fusion strategy to integrate both linear and locally linear structures from a global perspective. Therefore, JetBGC unifies robust representation learning, flexible anchor optimization, and structural bipartite graph fusion in a framework. Extensive experiments on synthetic and real-world datasets validate our effectiveness against existing baselines.

In recent years, multi-view unsupervised feature selection has gained significant interest for its ability to efficiently handle multi-view datasets while offering better interpretability. However, most existing methods face the following challenges: First, the presence of noisy features in the data significantly impacts the process of learning accurate feature importance. Second, the selected features contain redundant information due to ignored redundancy between them. Third, graph structure learning is performed on all samples, resulting in large computational and space overheads, which is not conducive to expansion to large-scale data. To address these challenges, we propose a multi-view unsupervised feature selection method based on latent semantics and anchor graph learning. Specifically, this method designs a feature-weighted orthogonal regression and subspace learning framework to suppress noise interference in the consensus latent semantics discovery and anchor graph construction process, enhance the robustness of multi-view representation learning and reduce the computation of graph construction. Meanwhile, the proposed method employs explicit redundancy mitigation mechanisms that penalize discriminative weight allocation to highly correlated features. Furthermore, the proposed method unifies feature weighting, consensus latent semantics discovery, and adaptive graph learning within a multi-layer learning framework, enabling comprehensive feature importance evaluation through interactive learning between multiple layers. Finally, an efficient iterative algorithm is designed to solve the proposed model. The superiority of the proposed algorithm is demonstrated by comparing it with seven state-of-the-art algorithms on seven public multi-view datasets.

Graph-based multi-view clustering methods have demonstrated satisfying performance by effectively capturing relationships among data samples. However, most existing methods primarily emphasize direct pairwise relationships, neglecting the exploration of high-order correlations present within each view. To this end, a novel approach, called multiview clustering via high-order bipartite graph learning and tensor low-rank representation (HBGTLRR), is proposed. Specifically, we first construct high-order bipartite graphs to capture latent relationships and concatenate them into a tensor. By applying tensor nuclear norm (TNN) minimization, we obtain a low-rank representation that reduces noise and preserves high-order consistency. Subsequently, a consensus graph is constructed by adaptively fusing the high-order bipartite graphs with corresponding weights, and then a Laplacian low-rank constraint is imposed on it to effectively capture the intrinsic data structure. Finally, extensive experimental results show that HBGTLRR significantly outperforms existing methods, thereby validating the effectiveness of our proposed method.

Multi-view graph clustering (MVGC) explores pairwise correlations of entire instances and comprehensively aggregates diverse source information with optimal graph structure. One major issue of practical MVGC is the high time and space complexities prohibiting being applied on large-scale applications. As a promising solution of addressing large-scale problems, anchor-based strategy identifies small portion and key landmarks to serve as replacements for the entire dataset. Despite of its efficiency, anchors chosen across views may be semantically unaligned contrasting to naturally-aligned full sample setting, which may lead to the latter inappropriate graph fusion. Limited attention has been focused on the mentioned Multi-View Anchor-Unaligned Problem (MV-AUP) in the existing literature. In this paper, we first revisit existing multi-view anchor graph clustering frameworks and present the MV-AUP phenomenon. Then, we propose a novelMulti-viewCorrespondingAnchorGraphAlignmentFusion framework (MV-CAGAF), which elegantly solves MV-AUP with structural representation matching in multi-dimensional spaces. Further, we theoretically prove our proposed structural matching approach can be regarded as minimizing the EMD distance of the two relative anchor distributions. Based on this, we design the innovative multi-view anchor graph fusion paradigm with correspondence alignment, which inherits the linear sample complexity for scalable cross-view clustering. Our proposed MV-CAGAF achieves significant improvements with the help of the novel fusion framework on comprehensive benchmark datasets. Most importantly, the experimental results on both of the simulated and real-world datasets significantly prove the importance of cross-view alignment for large-scale multi-view clustering.

Graph anomaly detection (GAD) on attributed networks aims to capture abnormal nodes whose attributes or structures differ significantly from most nodes. The existing GAD models amplify the representation differences between normal and abnormal nodes to identify anomalies via carefully designed feature extraction modules. However, these models ignore the bottlenecks encountered by abnormal nodes in message passing. In particular, when the anomalies occurs at critical crossroads, the information of multiple nodes is compressed into a fixed-length representation, and the resulting over-squashing weakens the abnormal information. To address this, we propose an unsupervisedSTructural optimization model guided by sIMilarity reconstruction (STIM). Specifically, we define redundant edges that cause over-squashing, design the Neighbor-Structure Optimization module to filter redundant edges through the edge-dropping strategy based on critical crossroads, and optimize the graph structure to alleviate over-squashing. In addition, to alleviate the over-smoothing caused by the high inter-class node similarity of the data itself and the edge-dropping strategy, we design the Neighbor-Similarity Reconstruction module based on similarity calculation, which guides the model to expand inter-class variation. Extensive experiments on benchmark datasets show that STIM can effectively optimize message passing and improve anomaly detection performance. The source code is available athttps://github.com/Junyi-Yan/STIM.

Deep learning has been widely applied in recommender systems, which has recently achieved revolutionary progress. However, most existing learning-based methods assume that the user and item distributions remain unchanged between the training phase and the test phase. However, the distribution of user and item features can naturally shift in real-world scenarios, potentially resulting in a substantial decrease in recommendation performance. This phenomenon can be formulated as an Out-Of-Distribution (OOD) recommendation problem. To address this challenge, we propose a novelDualTest-Time-Training framework forOODRecommendation, termedDT3OR. In DT3OR, we incorporate a model adaptation mechanism during the test-time phase to carefully update the recommendation model, allowing the model to adapt specially to the shifting user and item features. To be specific, we propose a self-distillation task and a contrastive task to assist the model learning both the user’s invariant interest preferences and the variant user/item characteristics during the test-time phase, thus facilitating a smooth adaptation to the shifting features. Furthermore, we provide theoretical analysis to support the rationale behind our dual test-time training framework. To the best of our knowledge, this paper is the first work to address OOD recommendation via a test-time-training strategy. We conduct experiments on five datasets with various backbones. Comprehensive experimental results have demonstrated the effectiveness of DT3OR compared to other state-of-the-art baselines.

The ubiquity of Graph Neural Networks (GNNs) emphasizes the imperative to assess their resilience against node injection attacks, a type of evasion attacks that impact victim models by injecting nodes with fabricated attributes and structures. However, prevailing attacks face two primary limitations: (1) Sequential construction of attributes and structures results in suboptimal outcomes as structure information is overlooked during attribute construction and vice versa. (2) In black-box scenarios, where attackers lack access to victim model architecture and parameters, reliance on surrogate models degrades performance due to architectural discrepancies. To overcome these limitations, we introduce GZOO, a black-box node injection attack that leverages an adversarial graph generator, compromising both attribute and structure sub-generators. This integration crafts optimal attributes and structures by considering their mutual information, enhancing their influence when aggregating information from injected nodes. Furthermore, GZOO proposes a zeroth-order optimization algorithm leveraging prediction results from victim models to estimate gradients for updating generator parameters, eliminating the necessity to train surrogate models. Across sixteen datasets, GZOO significantly outperforms state-of-the-art attacks, achieving remarkable effectiveness and robustness. Notably, on the Cora dataset with the GCN model, GZOO achieves an impressive 95.69% success rate, surpassing the maximum 66.01% achieved by baselines.

Dynamic ensemble has significantly greater potential space to improve the classification of imbalanced data compared to static ensemble. However, dynamic ensemble schemes are far less successful than static ensemble methods in the imbalanced learning field. Through an in-depth analysis on the behavior characteristics of dynamic ensemble, we find that there are some important problems that need to be addressed to release the full potential of dynamic ensemble, including but not limited to, correcting the component classifiers’ bias towards the majority classes, increasing the proportions of the positive classifiers (i.e., the component classifiers making correct prediction) for difficult samples, and providing the accurate competence estimations on the hard-to-classify samples w.r.t the classifier pool. Inspired by these, we propose a Dynamic Ensemble Framework for imbalanced data classification (imDEF). imDEF first uses the data generation method OREM$\mathrm{_{G}}$to generate multiple artificial synthetic datasets, which have diverse class distributions by rebalancing the original imbalanced data. Based on each of such synthetic datasets, imDEF then utilizes a Classification Error-aware Self-Paced Sampling Ensemble (SPSE$\mathrm{_{CE}}$) method to gradually focus more on difficult samples, to create a low-biased classifier pool and increase the proportions of the positive classifiers for the difficult samples. Finally, imDEF constructs a referee system to achieve the competence estimations by leveraging an Ensemble Margin-aware Self-Paced Sampling Ensemble (SPSE$\mathrm{_{EM}}$) method. SPSE$\mathrm{_{EM}}$incrementally strengthens the learning of the hard-to-classify samples, so that the competent levels of component classifiers could be estimated accurately. Extensive experiments demonstrate the effectiveness of imDEF. The source codes have been made publicly available on GitHub.

Attribute-missing deep graph clustering, which aims to categorize the graph nodes with partial attribute-missing samples into distinct categories in an unsupervised manner, has gained significant popularity. However, most existing researches have at least one of the following issues: 1) seldom exploit diverse clustering structural information to facilitate non-Euclidean data imputation and refine the clustering pattern and 2) ignoring the positive effect of diverse information on feature imputation and representation extraction, resulting in sub-optimal missing feature estimation and inferior clustering performance. To solve these issues, we propose a novelPrototype-drivenMulti-viewAttribute-missingGraphClustering (PMAGC) model that leverages rich structural and diverse information to assist the processes of imputing missing attributes and learning clustering-friendly features. Specifically, we design a multi-view augmentation module that extracts attribute-complete samples as node view and constructs feature and edge views using feature pre-imputation and edge masking techniques. Then, guided by clustering pseudo-labels, we promote the proximity between the prototypes of attribute-missing samples and those of attribute-complete samples within the feature space. Thus, PMAGC cleverly employs both clustering structural information and reliably attribute-complete sample data to assist feature imputation. In addition, we design a prototype-wise contrastive loss, which considers prototypes from different views within the same cluster as positive samples, while treating others as negative samples. Hence, the optimized features could more accurately guide the attribute learning process. Extensive experiments on six graph datasets with missing attributes are conducted to demonstrate the effectiveness of the proposed PMAGE.

Hyperspectral images with high spectral resolution provide new insights into recognizing subtle differences in similar substances. However, object detection in hyperspectral images faces significant challenges in intra- and inter-class similarity due to the spatial differences in hyperspectral inter-bands and unavoidable interferences, e.g., sensor noises and illumination. To alleviate the hyperspectral inter-bands inconsistencies and redundancy, we propose a novel network termedSpectralDiscrepancy andCross-Modal semantic consistency learning (SDCM), which facilitates the extraction of consistent information across a wide range of hyperspectral bands while utilizing the spectral dimension to pinpoint regions of interest. Specifically, we leverage a semantic consistency learning (SCL) module that utilizes inter-band contextual cues to diminish the heterogeneity of information among bands, yielding highly coherent spectral dimension representations. On the other hand, we incorporate a spectral gated generator (SGG) into the framework that filters out the redundant data inherent in hyperspectral information based on the importance of the bands. Then, we design the spectral discrepancy aware (SDA) module to enrich the semantic representation of high-level information by extracting pixel-level spectral features. Extensive experiments on two hyperspectral datasets demonstrate that our proposed method achieves state-of-the-art performance when compared with other ones.

Site selection aims to select optimal locations for new stores, which is crucial in business management and urban computing. The early data-driven models heavily relied on feature engineering, which could not effectively model the complex relationships and diverse influences among different data. To alleviate such issues, the knowledge-driven paradigm is proposed based on urban knowledge graphs (KGs). However, the research on them is at an early stage. They omit extra multi-modal information corresponding to brands and stores due to two main challenges, i.e., (1) building available datasets, and (2) designing effective models. It constrains the expressive ability and practical value of previous models. To this end, we first construct new multi-modal urban KGs for site selection with three extra modal (i.e., visual, textual, and acoustic) attributes. Then, we propose a novel multi-modal knowledge-driven model (MGKsite). Concretely, a graph neural network (GNN) based fusion network is designed to fuse the features based on the attribute K-Nearest Neighbor (KNN) graph, which models both intra and inter-modal correlations among the features. The fused embeddings are further injected into the knowledge-driven backbones for learning and inference. Experiments prove promising capacities of MGKsite from five aspects, i.e., superiority, effectiveness, sensitivity, transferability and complexity.

Stance detection on social media aims to identify if an individual is in support of or against a specific target. Most existing stance detection approaches primarily rely on modeling the contextual semantic information in sentences and neglect to explore the pragmatics dependency information of words, thus degrading performance. Although several single-task learning methods have been proposed to capture richer semantic representation information, they still suffer from semantic sparsity problems caused by short texts on social media. This article proposes a novel multigraph sparse interaction network (MG-SIN) by using multitask learning (MTL) to identify the stances and classify the sentiment polarities of tweets simultaneously. Our basic idea is to explore the pragmatics dependency relationship between tasks at the word level by constructing two types of heterogeneous graphs, including task-specific and task-related graphs (tr-graphs), to boost the learning of task-specific representations. A graph-aware module is proposed to adaptively facilitate information sharing between tasks via a novel sparse interaction mechanism among heterogeneous graphs. Through experiments on two real-world datasets, compared with the state-of-the-art baselines, the extensive results exhibit that MG-SIN achieves competitive improvements of up to 2.1% and 2.42% for the stance detection task, and 5.26% and 3.93% for the sentiment analysis task, respectively.

Chain-of-thought distillation (CoT-distillation) aims to endow small language models (SLMs) with reasoning ability to improve their performance toward specific tasks by allowing them to imitate the reasoning procedure of large language models (LLMs) beyond simply predicting the answers. Most existing CoT-distillation methods adopt a pre-thinking mechanism, allowing the SLM to generate a rationale before answering. In this way, pre-thinking enables SLM to analyze questions but makes answer correctness sensitive to minor errors in rationale. Therefore, we propose a robust post-thinking mechanism to generate answers before the rationale. Thanks to this answer-first setting: 1) the answer can escape from the rationale-sensitive problem; 2) the rationale serves as an error amplifier, making SLM focus on learning hard samples; and 3) the inferring efficiency can also benefit. Although post-thinking brings many advantages, it may lose the ability to analyze complex questions compared to pre-thinking. Therefore, a plug-and-play adaptive-thinking mechanism is proposed to integrate the merits of pre-thinking and post-thinking, in which a perception module based on soft prompt tuning is introduced to prompt SLM to answer or think first according to the complexity of questions. Extensive experiments are conducted across 12 datasets and 2 language models to demonstrate the effectiveness of the proposed mechanism.

The success of multiview raw data mining relies on the integrity of attributes. However, each view faces various noises and collection failures, which leads to a condition that attributes are only partially available. To make matters worse, the attributes in multiview raw data are composed of multiple forms, which makes it more difficult to explore the structure of the data especially in multiview clustering task. Due to the missing data in some views, the clustering task on incomplete multiview data confronts the following challenges, namely: 1) mining the topology of missing data in multiview is an urgent problem to be solved; 2) most approaches do not calibrate the complemented representations with common information of multiple views; and 3) we discover that the cluster distributions obtained from incomplete views have a cluster distribution unaligned problem (CDUP) in the latent space. To solve the above issues, we propose a deep clustering framework based on subgraph propagation and contrastive calibration (SPCC) for incomplete multiview raw data. First, the global structural graph is reconstructed by propagating the subgraphs generated by the complete data of each view. Then, the missing views are completed and calibrated under the guidance of the global structural graph and contrast learning between views. In the latent space, we assume that different views have a common cluster representation in the same dimension. However, in the unsupervised condition, the fact that the cluster distributions of different views do not correspond affects the information completion process to use information from other views. Finally, the complemented cluster distributions for different views are aligned by contrastive learning (CL), thus solving the CDUP in the latent space. Our method achieves advanced performance on six benchmarks, which validates the effectiveness and superiority of our SPCC.

Since the rapid progress in multimedia and sensor technologies, multiview clustering (MVC) has become a prominent research area within machine learning and data mining, experiencing significant advancements over recent decades. MVC is distinguished from single-view clustering by its ability to integrate complementary information from multiple distinct data perspectives and enhance clustering performance. However, the efficacy of MVC methods is predicated on the availability of complete views for all samples-an assumption that frequently fails in practical scenarios where data views are often incomplete. To surmount this challenge, various approaches to incomplete MVC (IMVC) have been proposed, with deep neural networks emerging as a favored technique for their representation learning ability. Despite their promise, previous methods commonly adopt sample-level (e.g., features) or affinity-level (e.g., graphs) guidance, neglecting the discriminative label-level guidance (i.e., pseudo-labels). In this work, we propose a novel deep IMVC method termed pseudo-label propagation for deep IMVC (PLP-IMVC), which integrates high-quality pseudo-labels from the complete subset of incomplete data with deep label propagation networks to obtain improved clustering results. In particular, we first design a local model (PLP-L) that leverages pseudo-labels to their fullest extent. Then, we propose a global model (PLP-G) that exploits manifold regularization to mitigate the label noises, promote view-level information fusion, and learn discriminative unified representations. Experimental results across eight public benchmark datasets and three evaluation metrics prove our method's efficacy, demonstrating superior performance compared to 18 advanced baseline methods.

Graph anomaly detection (GAD) has gained increasing attention in various attribute graph applications, i.e., social communication and financial fraud transaction networks. Recently, graph contrastive learning (GCL)-based methods have been widely adopted as the mainstream for GAD with remarkable success. However, existing GCL strategies in GAD mainly focus on node-node and node-subgraph contrast and fail to explore subgraph-subgraph level comparison. Furthermore, the different sizes or component node indices of the sampled subgraph pairs may cause the "nonaligned" issue, making it difficult to accurately measure the similarity of subgraph pairs. In this article, we propose a novel subgraph-aligned multiview contrastive approach for graph anomaly detection, named SAMCL, which fills the subgraph-subgraph contrastive-level blank for GAD tasks. Specifically, we first generate the multiview augmented subgraphs by capturing different neighbors of target nodes forming contrasting subgraph pairs. Then, to fulfill the nonaligned subgraph pair contrast, we propose a subgraph-aligned strategy that estimates similarities with the Earth mover's distance (EMD) of both considering the node embedding distributions and typology awareness. With the newly established similarity measure for subgraphs, we conduct the interview subgraph-aligned contrastive learning module to better detect changes for nodes with different local subgraphs. Moreover, we conduct intraview node-subgraph contrastive learning to supplement richer information on abnormalities. Finally, we also employ the node reconstruction task for the masked subgraph to measure the local change of the target node. Finally, the anomaly score for each node is jointly calculated by these three modules. Extensive experiments conducted on benchmark datasets verify the effectiveness of our approach compared to existing state-of-the-art (SOTA) methods with significant performance gains (up to 6.36% improvement on ACM). Our code can be verified at https://github.com/hujingtao/SAMCL.

Video instance segmentation (VIS) is a challenging task, requiring handling object classification, segmentation, and tracking in videos. Existing Transformer-based VIS approaches have shown remarkable success, combining encoded features and instance queries as decoder inputs. However, their decoder inputs are low-resolution due to computational cost, resulting in a loss of fine-grained information, sensitivity to background interference, and poor handling of small objects. Moreover, the queries are randomly initialized without location information, hindering convergence efficiency and accurate object instance localization. To address these issues, we propose a novel VIS approach, STFormer, with a spatial-temporal feature aggregation (STFA) module and spatial-temporal-aware Transformer (STT). Specifically, STFA obtains robust high-resolution masked features efficiently for the decoder, while STT's location-guided instance query (LGIQ) improves initial instance queries. STFormer preserves more fine-grained information, improves convergence efficiency, and localizes object instance features accurately. Extensive experiments on YouTube-VIS 2019, YouTube-VIS 2021, and OVIS datasets show that STFormer outperforms mainstream VIS methods.

As an emerging task, temporal graph clustering (TGC) is committed to clustering nodes on temporal graphs through interaction sequence-based batch-processing patterns. These patterns allow for more flexibility in finding a balance between time and space requirements than adjacency matrix-based static graph clustering. However, as a new task, TGC still has important unresolved challenges, such as insufficient information. This challenge manifests itself in a variety of problems in real-world datasets, including missing features (eigenvalues are missing or even nonexistent), long-tail nodes (most inactive nodes have little interaction), and noisy data (data is subject to anomalies, errors, and sparsity). These problems occur before training, making it difficult for the model to train well with insufficient information. To solve the challenge, we propose a method that introduces multiview clustering (MVC) into TGC, called MVTGC. Our method aims to perform data augmentation on the temporal graph by constructing multiple views to increase the information richness. In particular, we utilize different techniques to model a certain part of the temporal graph to generate enhanced views focusing on different angles. These views are combined into training through early fusion and late fusion and ultimately enhance the model's receptive field and information richness. Comparative experiments and a case study on real-world datasets demonstrate the significance and effectiveness of MVTGC, which achieves at most 10.48% performance improvement. The code and data are available at https://github.com/MGitHubL/MVTGC.

Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information, which has recently garnered increasing attention. In contrast to static graphs, temporal graphs are typically organized as node interaction sequences over continuous time rather than an adjacency matrix. Most temporal graph learning methods model current interactions by incorporating historical neighborhood. However, such methods only consider first-order temporal information while disregarding crucial high-order structural information, resulting in suboptimal performance. To address this issue, we propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information to learn more informative node representations. Notably, the initial node representations combine first-order temporal and high-order structural information differently to calculate two conditional intensities. An alignment loss is then introduced to optimize the node representations, narrowing the gap between the two intensities and making them more informative. Concretely, in addition to modeling temporal information using historical neighbor sequences, we further consider structural knowledge at both local and global levels. At the local level, we generate structural intensity by aggregating features from high-order neighbor sequences. At the global level, a global representation is generated based on all nodes to adjust the structural intensity according to the active statuses on different nodes. Extensive experiments demonstrate that the proposed model S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.

Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different clusters without human annotations, is a fundamental yet challenging task. However, we observe that the existing methods suffer from the representation collapse problem and tend to encode samples with different classes into the same latent embedding. Consequently, the discriminative capability of nodes is limited, resulting in suboptimal clustering performance. To address this problem, we propose a novel deep graph clustering algorithm termed improved dual correlation reduction network (IDCRN) through improving the discriminative capability of samples. Specifically, by approximating the cross-view feature correlation matrix to an identity matrix, we reduce the redundancy between different dimensions of features, thus improving the discriminative capability of the latent space explicitly. Meanwhile, the cross-view sample correlation matrix is forced to approximate the designed clustering-refined adjacency matrix to guide the learned latent representation to recover the affinity matrix even across views, thus enhancing the discriminative capability of features implicitly. Moreover, we avoid the collapsed representation caused by the oversmoothing issue in graph convolutional networks (GCNs) through an introduced propagation regularization term, enabling IDCRN to capture the long-range information with the shallow network structure. Extensive experimental results on six benchmarks have demonstrated the effectiveness and efficiency of IDCRN compared with the existing state-of-the-art deep graph clustering algorithms. The code of IDCRN is released at IDCRN. Besides, we share a collection of deep graph clustering, including papers, codes, and datasets at ADGC.

Few-shot relation reasoning on knowledge graphs (FS-KGR) is an important and practical problem that aims to infer long-tail relations and has drawn increasing attention these years. Among all the proposed methods, self-supervised learning (SSL) methods, which effectively extract the hidden essential inductive patterns relying only on the support sets, have achieved promising performance. However, the existing SSL methods simply cut down connections between high-frequency and long-tail relations, which ignores the fact, i.e., the two kinds of information could be highly related to each other. Specifically, we observe that relations with similar contextual meanings, called aliasing relations (ARs), may have similar attributes. In other words, the ARs of the target long-tail relation could be in high-frequency, and leveraging such attributes can largely improve the reasoning performance. Based on the interesting observation above, we proposed a novel Self-supervised learning model by leveraging Aliasing Relations to assist FS-KGR, termed SARF. Specifically, we propose a graph neural network (GNN)-based AR-assist module to encode the ARs. Besides, we further provide two fusion strategies, i.e., simple summation and learnable fusion, to fuse the generated representations, which contain extra abundant information underlying the ARs, into the self-supervised reasoning backbone for performance enhancement. Extensive experiments on three few-shot benchmarks demonstrate that SARF achieves state-of-the-art (SOTA) performance compared with other methods in most cases.

Link prediction on temporal networks aims to predict the future edges by modeling the dynamic evolution involved in the graph data. Previous methods relying on the node/edge attributes or the distance on the graph structure are not practical due to the deficiency of the attributes and the limitation of the explicit distance estimation, respectively. Moreover, the existing graph representation learning methods mostly rely on graph neural networks (GNNs), which cannot adequately take the dynamic correlations between nodes into consideration, leading to the generating of inferior node embeddings. Thus, we propose a time-aware graph (TAG) learning method for link prediction on temporal networks. We first conduct a theoretical causal analysis proving that the correlations between nodes are required to be unchanged for the temporal graph representation learning using GNNs. Then, we model the recent dynamic node correlations by designing an edge-dropping (ED) module and adopting a recent neighbor sampling (RNS) strategy so as to approximate the above condition. Besides, we also preserve the long-term stable node correlations by introducing additional self-supervisions using the contrastive learning. Comprehensive experiments were conducted on four public temporal network datasets, i.e., MathOverflow, StackOverflow, AskUbuntu, and SuperUser, demonstrate that TAG can achieve state-of-the-art performance in terms of average precision (AP) and area under the ROC curve (AUC). In addition, TAG can ensure high computational efficiency by making the temporal graph lightweight, letting it be practical in real-world applications.

Inductive link prediction on temporal networks aims to predict the future links associated with node(s) unseen in the historical timestamps. Existing methods generate the predictions mainly by learning node representation from the node/edge attributes as well as the network dynamics or by measuring the distance between nodes on the temporal network structure. However, the attribute information is unavailable in many realistic applications and the structure-aware methods highly rely on nodes' common neighbors, which are difficult to accurately detect, especially in sparse temporal networks. Thus, we propose a distance-aware learning (DEAL) approach for inductive link prediction on temporal networks. Specifically, we first design an adaptive sampling method to extract temporal adaptive walks for nodes, increasing the probability of including the common neighbors between nodes. Then, we design a dual-channel distance measuring component, which simultaneously measures the distance between nodes in the embedding space and on the dynamic graph structure for predicting future inductive edges. Extensive experiments are conducted on three public temporal network datasets, i.e., MathOverflow, AskUbuntu, and StackOverflow. The experimental results validate the superiority of DEAL over the state-of-the-art baselines in terms of accuracy, area under the ROC curve (AUC), and average precision (AP), where the improvements are especially obvious in scenarios with only limited data.

In contrast to traditional single-view clustering methods, multiview clustering (MVC) approaches aim to extract, analyze, and integrate structural information from diverse perspectives, providing a more comprehensive understanding of internal data structures. However, with an increasing number of views, maintaining the integrity of view information becomes challenging, giving rise to incomplete MVC (IMVC) methods. While existing IMVC methods have shown notable performance on many incomplete multiview (IMV) databases, they still grapple with two key shortcomings: 1) they treat the information of each view as a whole, disregarding the differences among samples within each view; and 2) they rely on eigenvalue and eigenvector operations on the view matrix, limiting their scalability for large-scale samples and views. To overcome these limitations, we propose a novel multiview clustering with consistent information (IMVC-CI) of sample points. Our method explores the multiview information set of sample points to extract consensus structural information and subsequently restores unknown information in each view. Importantly, our approach operates independently on individual sample points, eliminating the need for eigenvalue and eigenvector operations on the view information matrix and facilitating parallel computation. This significantly enhances algorithmic efficiency and mitigates challenges associated with dimensionality. Experimental results on various public datasets demonstrate that our algorithm outperforms state-of-the-art IMVC methods in terms of clustering performance and computational efficiency. The code for our article has been uploaded to https://github.com/PhdJiayiTang/IMVC-CI.git.

With the development of various applications, such as recommendation systems and social network analysis, graph data have been ubiquitous in the real world. However, graphs usually suffer from being absent during data collection due to copyright restrictions or privacy-protecting policies. The graph absence could be roughly grouped into attribute-incomplete and attribute-missing cases. Specifically, attribute-incomplete indicates that a portion of the attribute vectors of all nodes are incomplete, while attribute-missing indicates that all attribute vectors of partial nodes are missing. Although various graph imputation methods have been proposed, none of them is custom-designed for a common situation where both types of graph absence exist simultaneously. To fill this gap, we develop a novel graph imputation network termed revisiting initializing then refining (RITR), where both attribute-incomplete and attribute-missing samples are completed under the guidance of a novel initializing-then-refining imputation criterion. Specifically, to complete attribute-incomplete samples, we first initialize the incomplete attributes using Gaussian noise before network learning, and then introduce a structure-attribute consistency constraint to refine incomplete values by approximating a structure-attribute correlation matrix to a high-order structure matrix. To complete attribute-missing samples, we first adopt structure embeddings of attribute-missing samples as the embedding initialization, and then refine these initial values by adaptively aggregating the reliable information of attribute-incomplete samples according to a dynamic affinity structure. To the best of our knowledge, this newly designed method is the first end-to-end unsupervised framework dedicated to handling hybrid-absent graphs. Extensive experiments on six datasets have verified that our methods consistently outperform the existing state-of-the-art competitors. Our source code is available at https://github.com/WxTu/RITR.

Multi-View clustering has attracted broad attention due to its capacity to utilize consistent and complementary information among views. Although tremendous progress has been made recently, most existing methods undergo high complexity, preventing them from being applied to large-scale tasks. Multi-View clustering via matrix factorization is a representative to address this issue. However, most of them map the data matrices into a fixed dimension, limiting the model's expressiveness. Moreover, a range of methods suffers from a two-step process, i.e., multimodal learning and the subsequent k-means, inevitably causing a suboptimal clustering result. In light of this, we propose a one-step multi-view clustering with diverse representation (OMVCDR) method, which incorporates multi-view learning and k-means into a unified framework. Specifically, we first project original data matrices into various latent spaces to attain comprehensive information and auto-weight them in a self-supervised manner. Then, we directly use the information matrices under diverse dimensions to obtain consensus discrete clustering labels. The unified work of representation learning and clustering boosts the quality of the final results. Furthermore, we develop an efficient optimization algorithm with proven convergence to solve the resultant problem. Comprehensive experiments on various datasets demonstrate the promising clustering performance of our proposed method. The code is publicly available at https://github.com/wanxinhang/OMVCDR.

Multiview clustering thrives in applications where views are collected in advance by extracting consistent and complementary information among views. However, it overlooks scenarios where data views are collected sequentially, i.e., real-time data. Due to privacy issues or memory burden, previous views are not available with time in these situations. Some methods are proposed to handle it but are trapped in a stability-plasticity dilemma. In specific, these methods undergo a catastrophic forgetting of prior knowledge when a new view is attained. Such a catastrophic forgetting problem (CFP) would cause the consistent and complementary information hard to get and affect the clustering performance. To tackle this, we propose a novel method termed contrastive continual multiview clustering with filtered structural fusion (CCMVC-FSF). Precisely, considering that data correlations play a vital role in clustering and prior knowledge ought to guide the clustering process of a new view, we develop a data buffer to store filtered structural information and utilize it to guide the generation of a robust partition matrix via contrastive learning. Additionally, to address the high complexity involved in acquiring and storing structural information, we propose a sampling strategy called clustering then sample. Furthermore, we theoretically connect CCMVC-FSF with semisupervised learning and knowledge distillation. Extensive experiments exhibit the excellence of the proposed method. Our code is publicly available at https://github.com/wanxinhang/CCMVC-FSF/.

Multimodal named entity recognition (MNER) is an emerging field that aims to automatically detect named entities and classify their categories, utilizing input text and auxiliary resources such as images. While previous studies have leveraged object detectors to preprocess images and fuse textual semantics with corresponding image features, these methods often overlook the potential finer grained information within each modality and may exacerbate error propagation due to predetection. To address these issues, we propose a finer grained rank-based contrastive learning (FRCL) framework for MNER. This framework employs a global-level contrastive learning to align multimodal semantic features and a Top-K rank-based mask strategy to construct positive-negative pairs, thereby learning a finer grained multimodal interaction representation. Experimental results from three well-known social media datasets reveal that our approach surpasses existing strong baselines, and achieves up to a 1.54% improvement on the Twitter2015 dataset. Extensive discussions further confirm the effectiveness of our approach. We will release the source code on https://github.com/augusyan/FRCL.

Clustering has attracted more and more attention as one of the most fundamental techniques in the field of unsupervised learning. To deal with nonlinear problems, clustering methods have been extended to the kernel version. As a traditional kernel clustering algorithm, multiple kernel k-means (MKKM) aims to learn clustering results from a consensus kernel obtained by combining a set of predefined kernels optimally. However, we observe that the existing MKKM algorithm and its variants insufficiently consider the noise that existed in kernel space and the underlying structure of kernelized data points. To this end, we propose a novel smooth MKKM via underlying graph filtering (SMKKM-UGF) to learn the smooth representations of kernelized data points through their nearby nodes in the underlying graph. In particular, different from the common graph filter, we jointly update the graph filter while learning the smooth kernel, so that the graph filter can be guaranteed to adapt to the updating kernel space constantly. Besides, an iterative algorithm with proven convergence is designed to solve the resultant optimization problem. Extensive experiments have been performed on numerous benchmark datasets, whose results prove the superiority of the proposed SMKKM-UGF compared to the other state-of-the-art clustering methods. The demo code of this work is publicly available at https://github.com/wqyang23/SMKKM-UGF.git.

Anchor technology is popularly employed in multi-view subspace clustering (MVSC) to reduce the complexity cost. However, due to the sampling operation being performed on each individual view independently and not considering the distribution of samples in all views, the produced anchors are usually slightly distinguishable, failing to characterize the whole data. Moreover, it is necessary to fuse multiple separated graphs into one, which leads to the final clustering performance heavily subject to the fusion algorithm adopted. What is worse, existing MVSC methods generate dense bipartite graphs, where each sample is associated with all anchor candidates. We argue that this dense-connected mechanism will fail to capture the essential local structures and degrade the discrimination of samples belonging to the respective near anchor clusters. To alleviate these issues, we devise a clustering framework named SL-CAUBG. Specifically, we do not utilize sampling strategy but optimize to generate the consensus anchors within all views so as to explore the information between different views. Based on the consensus anchors, we skip the fusion stage and directly construct the unified bipartite graph across views. Most importantly, norm and Laplacian-rank constraints employed on the unified bipartite graph make it capture both local and global structures simultaneously. norm helps eliminate the scatters between anchors and samples by constructing sparse links and guarantees our graph to be with clear anchor-sample affinity relationship. Laplacian-rank helps extract the global characteristics by measuring the connectivity of unified bipartite graph. To deal with the nondifferentiable objective function caused by norm, we adopt an iterative re-weighted method and the Newton's method. To handle the nonconvex Laplacian-rank, we equivalently transform it as a convex trace constraint. We also devise a four-step alternate method with linear complexity to solve the resultant problem. Substantial experiments show the superiority of our SL-CAUBG.

Clustering is a popular research pipeline in unsupervised learning to find potential groupings. As a representative paradigm in multiple kernel clustering (MKC), late fusion-based models learn a consistent partition across multiple base kernels. Despite their promising performance, a common concern is the limited representation capacity caused by the inflexible fusion mechanism. Concretely, the representations are constrained by truncated-k Eigen-decomposition (EVD) without fully exploiting potential information. An intuitive idea to alleviate this concern is to generate a set of augmented partitions and then select the optimal partition by fine-tuning. However, this is overlimited by: 1) introducing undesired hyperparameters and dataset-related consequences; 2) neglecting rich information across diverse partitions; and 3) expensive parameter-tuning costs. To address these problems, we propose transforming the challenging problem of directly determining the optimal partition (optimal parameter) into a diverse partition fusion (parameter ensemble) problem. We design a novel flexible fusion mechanism called tuning-free multiple kernel clustering coupled with diverse partition fusion (TFMKC) by reweighting diverse partitions through optimization, achieving an optimal consensus partition by integrating diverse and complementary information rather than traditional fine-tuning, and distinguishing our work from existing methods. Extensive experiments verify that TFMKC achieves competitive effectiveness and efficiency over comparison baselines. The code can be accessed at https://github.com/ZJP/TFMKC.

Multiview clustering has become a prominent research topic in data analysis, with wide-ranging applications across various fields. However, the existing late fusion multiview clustering (LFMVC) methods still exhibit some limitations, including variable importance and contributions and a heightened sensitivity to noise and outliers during the alignment process. To tackle these challenges, we propose a novel regularized instance weighting multiview clustering via late fusion alignment (R-IWLF-MVC), which considers the instance importance from various views, enabling information integration to be more effective. Specifically, we assign each sample an importance attribute to enable the learning process to focus more on the key sample nodes and avoid being influenced by noise or outliers, while laying the groundwork for the fusion of different views. In addition, we continue to employ late fusion alignment to integrate base clustering from various views and introduce a new regularization term with prior knowledge to ensure that the learning process does not deviate too much from the expected results. After that, we design a three-step alternating optimization strategy with proven convergence for the resultant problem. Our proposed approach has been extensively evaluated on multiple real-world datasets, demonstrating its superiority to state-of-the-art methods.

While humans can excel at image classification tasks by comparing a few images, existing metric-based few-shot classification methods are still not well adapted to novel tasks. Performance declines rapidly when encountering new patterns, as feature embeddings cannot effectively encode discriminative properties. Moreover, existing matching methods inadequately utilize support set samples, focusing only on comparing query samples to category prototypes without exploiting contrastive relationships across categories for discriminative features. In this work, we propose a method where query samples select their most category-representative features for matching, making feature embeddings adaptable and category-related. We introduce a category alignment mechanism (CAM) to align query image features with different categories. CAM ensures features chosen for matching are distinct and strongly correlated to intra- and inter-contrastive relationships within categories, making extracted features highly related to their respective categories. CAM is parameter-free, requires no extra training to adapt to new tasks, and adjusts features for matching when task categories change. We also implement a cross-validation-based feature selection technique for support samples, generating more discriminative category prototypes. We implement two versions of inductive and transductive inference and conduct extensive experiments on six datasets to demonstrate the effectiveness of our algorithm. The results indicate that our method consistently yields performance improvements on benchmark tasks and surpasses the current state-of-the-art methods.

This article introduces a novel latent 3D diffusion model for generating neural voxel fields with precise part-aware structures and high-quality textures. In comparison to existing methods, this approach incorporates two key designs to guarantee high-quality and accurate part-aware generation. On one hand, we introduce a latent 3D diffusion process for neural voxel fields, incorporating part-aware information into the diffusion process and allowing generation at significantly higher resolutions to capture rich textural and geometric details accurately. On the other hand, a part-aware shape decoder is introduced to integrate the part codes into the neural voxel fields, guiding accurate part decomposition and producing high-quality rendering results. Importantly, part-aware learning establishes structural relationships to generate texture information for similar regions, thereby facilitating high-quality rendering results. We evaluate our approach across eight different data classes through extensive experimentation and comparisons with state-of-the-art methods. The results demonstrate that our proposed method has superior generative capabilities in part-aware shape generation, outperforming existing state-of-the-art methods. Moreover, we have conducted image- and text-guided shape generation via the conditioned diffusion process, showcasing the advanced potential in multi-modal guided shape generation.

Crime prediction is a crucial yet challenging task within urban computing, which benefits public safety and resource optimization. Over the years, various models have been proposed, and spatial-temporal hypergraph learning models have recently shown outstanding performances. However, three correlations underlying crime are ignored, thus hindering the performance of previous models. Specifically, there are two spatial correlations and one temporal correlation, i.e., (1) co-occurrence of different types of crimes (type spatial correlation), (2) the closer to the crime center, the more dangerous it is around the neighborhood area (neighbor spatial correlation), and (3) the closer between two timestamps, the more relevant events are (hawkes temporal correlation). To this end, we propose Hawkes-enhanced Spatial-Temporal Hypergraph Contrastive Learning framework (HCL), which mines the aforementioned correlations via two specific strategies. Concretely, contrastive learning strategies are designed for two spatial correlations, and hawkes process modeling is adopted for temporal correlations. Extensive experiments demonstrate the promising capacities of HCL from four aspects, i.e., superiority, transferability, effectiveness, and sensitivity.

GraIL and its variants have shown their promising capacities for inductive relation reasoning on knowledge graphs. However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs. Besides, the enclosing subgraph extraction in most GraIL-based models restricts the model from extracting enough discriminative information for reasoning. Consequently, the expressive ability of these models is limited. To address the problems, we propose a novel GraIL-based framework, termed MINES, by introducing a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Concretely, the message intercommunication mechanism is designed to capture the omitted hidden mutual information. It introduces bi-directed information interactions between connected entities by inserting an undirected/bi-directed GCN layer between uni-directed RGCN layers. Moreover, inspired by the success of involving more neighbors in other graph-based tasks, we extend the neighborhood area beyond the enclosing subgraph to enhance the information collection for inductive relation reasoning. Extensive experiments prove the promising capacity of the proposed MINES from various aspects, especially for the superiority, effectiveness, and transfer ability.

Incomplete multi-view clustering has attracted much attention due to its ability to handle partial multi-view data. Recently, similarity-based methods have been developed to explore the complete relationship among incomplete multi-view data. Although widely applied to partial scenarios, most of the existing approaches are still faced with two limitations. Firstly, fusing similarities constructed individually on each view fails to yield a complete unified similarity. Moreover, incomplete similarity generation may lead to anomalous similarity values with column sum constraints, affecting the final clustering results. To solve the above challenging issues, we propose a Sample-level Cross-view Similarity Learning (SCSL) method for Incomplete Multi-view Clustering. Specifically, we project all samples to the same dimension and simultaneously construct a complete similarity matrix across views based on the inter-view sample relationship and the intra-view sample relationship. In addition, a simultaneously learning consensus representation ensures the validity of the projection, which further enhances the quality of the similarity matrix through the graph Laplacian regularization. Experimental results on six benchmark datasets demonstrate the ability of SCSL in processing incomplete multi-view clustering tasks. Our code is publicly available at https://github.com/Tracesource/SCSL.

Deep clustering with attribute-missing graphs, where only a subset of nodes possesses complete attributes while those of others are missing, is an important yet challenging topic in various practical applications. It has become a prevalent learning paradigm in existing studies to perform data imputation first and subsequently conduct clustering using the imputed information. However, these ``two-stage" methods disconnect the clustering and imputation processes, preventing the model from effectively learning clustering-friendly graph embedding. Furthermore, they are not tailored for clustering tasks, leading to inferior clustering results. To solve these issues, we propose a novel Attribute-Missing Graph Clustering (AMGC) method to alternately promote clustering and imputation in a unified framework, where we iteratively produce the clustering-enhanced nearest neighbor information to conduct the data imputation process and utilize the imputed information to implicitly refine the clustering distribution through model optimization. Specifically, in the imputation step, we take the learned clustering information as imputation prompts to help each attribute-missing sample gather highly correlated features within its clusters for data completion, such that the intra-class compactness can be improved. Moreover, to support reliable clustering, we maximize inter-class separability by conducting cost-efficient dual non-contrastive learning over the imputed latent features, which in turn promotes greater graph encoding capability for clustering sub-network. Extensive experiments on five datasets have verified the superiority of AMGC against competitors.

In numerous real-world applications, it is quite common that sample information is partially available for some views due to machine breakdown or sensor failure, causing the problem of incomplete multi-view clustering (IMVC). While several IMVC approaches using view-shared anchors have successfully achieved pleasing performance improvement, (1) they generally construct anchors with only one dimension, which could deteriorate the multi-view diversity, bringing about serious information loss; (2) the constructed anchors are typically with a single size, which could not sufficiently characterize the distribution of the whole samples, leading to limited clustering performance. For generating view-shared anchors with multi-dimension and multi-size for IMVC, we design a novel framework called Diverse View-Shared Anchors based Incomplete multi-view clustering (DVSAI). Concretely, we associate each partial view with several potential spaces. In each space, we enable anchors to communicate among views and generate the view-shared anchors with space-specific dimension and size. Consequently, spaces with various scales make the generated view-shared anchors enjoy diverse dimensions and sizes. Subsequently, we devise an integration scheme with linear computational and memory expenditures to integrate the outputted multi-scale unified anchor graphs such that running spectral algorithm generates the spectral embedding. Afterwards, we theoretically demonstrate that DVSAI owns linear time and space costs, thus well-suited for tackling large-size datasets. Finally, comprehensive experiments confirm the effectiveness and advantages of DVSAI.

In recent years, anchor-based methods have achieved promising progress in multi-view clustering. The performances of these methods are significantly affected by the quality of the anchors. However, the anchors generated by previous works solely rely on single-view information, ig-noring the correlation among different views. In particular, we observe that similar patterns are more likely to exist between similar views so such correlation information can be leveraged to enhance the quality of the anchors, which is also omitted. To this end, we propose a novel plug-and-play anchor enhancement strategy through view correlation for multi-view clustering. Specifically, we construct a view graph based on aligned initial anchor graphs to explore inter-view correlations. By learning from view correlation, we enhance the anchors of the current view using the relationships between anchors and samples on neighboring views, thereby narrowing the spatial distribution of anchors on similar views. Experimental results on seven datasets demonstrate the superiority of our proposed method over other existing methods. Furthermore, extensive comparative experiments validate the effectiveness of the proposed anchor enhancement module when applied to various anchor-based methods.

Deep graph clustering has recently received significant attention due to its ability to enhance the representation learning capabilities of models in unsupervised scenarios. Nevertheless, deep clustering for temporal graphs, which could capture crucial dynamic interaction information, has not been fully explored. It means that in many clustering-oriented real-world scenarios, temporal graphs can only be processed as static graphs. This not only causes the loss of dynamic information but also triggers huge computational consumption. To solve the problem, we propose a general framework for deep Temporal Graph Clustering called TGC, which introduces deep clustering techniques to suit the interaction sequence-based batch-processing pattern of temporal graphs. In addition, we discuss differences between temporal graph clustering and static graph clustering from several levels. To verify the superiority of the proposed framework TGC, we conduct extensive experiments. The experimental results show that temporal graph clustering enables more flexibility in finding a balance between time and space requirements, and our framework can effectively improve the performance of existing temporal graph learning methods. The code is released: https://github.com/MGitHubL/Deep-Temporal-Graph-Clustering.

In this paper, we derive an upper bound of the difference between a kernel matrix and its expectation under a mild assumption. Specifically, we assume that the true distribution of the training data is an unknown isotropic Gaussian distribution. When the kernel function is a Gaussian kernel, and the mean of each cluster is sufficiently separated, we find that the expectation of a kernel matrix can be close to a rank-$k$ matrix, where $k$ is the cluster number. Moreover, we prove that the normalized kernel matrix of the training set deviates (w.r.t. Frobenius norm) from its expectation in the order of $\widetilde{\mathcal{O}}(1/\sqrt{d})$, where $d$ is the dimension of samples. Based on the above theoretical results, we propose a novel multiple kernel clustering framework which attempts to learn the information of the expectation kernel matrices. First, we aim to minimize the distance between each base kernel and a rank-$k$ matrix, which is a proxy of the expectation kernel. Then, we fuse these rank-$k$ matrices into a consensus rank-$k$ matrix to find the clustering structure. Using an anchor-based method, the proposed framework is flexible with the sizes of input kernel matrices and able to handle large-scale datasets. We also provide the approximation guarantee by deriving two non-asymptotic bounds for the consensus kernel and clustering indicator matrices. Finally, we conduct extensive experiments to verify the clustering performance of the proposed method and the correctness of the proposed theoretical results.

Sample labeling is the most primary and fundamental step of semi-supervised learning. In literature, most existing methods randomly label samples with a given ratio, but achieve unpromising and unstable results due to the randomness, especially in multi-view settings. To address this issue, we propose a Dynamic Multi-view Labeling Strategy with Shared and Specific Information. To be brief, by building two classifiers with existing labels to utilize decoupled shared and specific information, we select the samples of low classification confidence and label them in high priorities. The newly generated labels are also integrated to update the classifiers adaptively. The two processes are executed alternatively until a satisfying classification performance. To validate the effectiveness of the proposed method, we conduct extensive experiments on popular benchmarks, achieving promising performance. The code is publicly available at https://github.com/wanxinhang/ICML2024_decouple_then_classify.

Incomplete multi-view clustering (IMVC) methods typically encounter three drawbacks: (1) intense time and/or space overheads; (2) intractable hyper-parameters; (3) non-zero variance results. With these concerns in mind, we give a simple yet effective IMVC scheme, termed as ToRES. Concretely, instead of self-expression affinity, we manage to construct prototype-sample affinity for incomplete data so as to decrease the memory requirements. To eliminate hyper-parameters, besides mining complementary features among views by view-wise prototypes, we also attempt to devise cross-view prototypes to capture consensus features for jointly forming high-quality clustering representation. To avoid the variance, we successfully unify representation learning and clustering operation, and directly optimize the discrete cluster indicators from incomplete data. Then, for the resulting objective function, we provide two equivalent solutions from perspectives of feasible region partitioning and objective transformation. Many results suggest that ToRES exhibits advantages against 20 SOTA algorithms, even in scenarios with a higher ratio of incomplete data.

Attribute networks are commonly used graph structures in complex application domains. With the increasing prominence of security issues, the detection of anomalies in attributed networks has become a widely studied topic. In recent years, anomaly detection methods based on graph deep learning have become increasingly popular. However, current research primarily focuses on undirected attributed networks. These methods fail to fully utilize the directional information of edges when facing directed networks which are widely present in reality, resulting in suboptimal performance. In order to tackle this problem, we propose a new self-supervised framework for anomaly detection in directed attributed networks, referred to as UDGAD. Our framework includes a novel bidirectional subgraph constructing algorithm that distinguishes the direction of edges, effectively leveraging the complex topological structure of directed networks. Furthermore, we propose a self-supervised model based on graph autoencoder and graph neural networks, which explores anomalies from the perspectives of attribute reconstruction and neighborhood matching. Finally, we evaluate anomaly degree of all nodes by multi-round computational evaluation. Experimental results demonstrate that our method outperforms traditional anomaly detection methods on directed attributed networks with ground truth labels.

Various information in different modalities in an intuitive way in multi-modal knowledge graphs (MKGs), which are utilized in different downstream tasks, like recommendation. However, most MKGs are still far from complete, which motivates the flourishing of MKG reasoning models. Recently, with the development of general artificial intelligence, pre-trained transformers have drawn increasing attention, especially in multi-modal scenarios. However, the research of multi-modal pre-trained transformers (MPT) for knowledge graph reasoning (KGR) is still at an early stage. As the biggest difference between MKG and other multi-modal data, the rich structural information underlying the MKG is still not fully utilized in previous MPT. Most of them only use the graph structure as a retrieval map for matching images and texts connected with the same entity, which hinders their reasoning performances. To this end, the graph Structure Guided Multi-modal Pre-trained Transformer is proposed for knowledge graph reasoning (SGMPT). Specifically, the graph structure encoder is adopted for structural feature encoding. Then, a structure-guided fusion module with two simple yet effective strategies, i.e., weighted summation and alignment constraint, is designed to inject the structural information into both the textual and visual features. To the best of our knowledge, SGMPT is the first MPT for multi-modal KGR, which mines structural information underlying MKGs. Extensive experiments on FB15k-237-IMG and WN18-IMG, demonstrate that our SGMPT outperforms existing state-of-the-art models, and proves the effectiveness of the designed strategies.

Spatial transcriptomics provides revolutionary insights into cellular interactions and disease development mechanisms by combining high-throughput gene sequencing and spatially resolved imaging technologies to analyze genes naturally associated with spatially variable tissue genes. However, existing methods typically map aggregated multi-view features into a unified representation, ignoring the heterogeneity and view independence of genes and spatial information. To this end, we construct a heterogeneous Graph guided Contrastive Learning (stGCL) for aggregating spatial transcriptomics data. The method is guided by the inherent heterogeneity of cellular molecules by dynamically coordinating triple-level node attributes through comparative learning loss distributed across view domains, thus maintaining view independence during the aggregation process. In addition, we introduce a cross-view hierarchical feature alignment module employing a parallel approach to decouple spatial and genetic views on molecular structures while aggregating multi-view features according to information theory, thereby enhancing the integrity of inter- and intra-views. Rigorous experiments demonstrate that stGCL outperforms existing methods in various tasks and related downstream applications.

Multi-view clustering (MVC) constitutes a distinct approach to data mining within the field of machine learning. Due to limitations in the data collection process, missing attributes are frequently encountered. However, existing MVC methods primarily focus on missing instances, showing limited attention to missing attributes. A small number of studies employ the reconstruction of missing instances to address missing attributes, potentially overlooking the synergistic effects between the instance and feature spaces, which could lead to distorted imputation outcomes. Furthermore, current methods uniformly treat all missing attributes as zero values, thus failing to differentiate between real and technical zeroes, potentially resulting in data over-imputation. To mitigate these challenges, we introduce a novel Reliable Attribute-Missing Multi-View Clustering method (RAM-MVC). Specifically, feature reconstruction is utilized to address missing attributes, while similarity graphs are simultaneously constructed within the instance and feature spaces. By leveraging structural information from both spaces, RAM-MVC learns a high-quality feature reconstruction matrix during the joint optimization process. Additionally, we introduce a reliable imputation guidance module that distinguishes between real and technical attribute-missing events, enabling discriminative imputation. The proposed RAM-MVC method outperforms nine baseline methods, as evidenced by real-world experiments using single-cell multi-view data.

Multi-View Clustering (MVC) commonly utilizes the anchor technique to mitigate the computational complexity. Existing methods generally assume a pre-selection of anchors to facilitate subsequent clustering tasks. However, the determination of the optimal number of anchors is often non-trivial and necessitates their treatment as a tunable parameter, incurring additional computational overhead. Moreover, it is not reasonable to assume an identical number of anchors across all views, as this assumption restricts the representational capacity of anchors in individual views. To address the above issues, we propose a view adaptive anchor multi-view clustering called Multi-view Clustering with Automatic and Aligned Anchor (3AMVC). We introduce a Hierarchical Bipartite Neighbor Clustering (HBNC) strategy to adaptively select a suitable number of representative anchors in each view. Specifically, when the representative difference of anchors lies in a acceptable and satisfactory range, the HBNC process is halted and picks out the final anchors. Moreover, we propose an innovative anchor alignment strategy in response to the varying quantities of anchors across different views. This approach initially evaluates the quality of anchors on each view based on the intra-cluster distance criterion and then proceeds to align based on the view with the highest-quality anchors. The carefully organized experiments well validate the effectiveness and strengthens of 3AMVC.

The rapid development of multi-media techniques boosts the emergence of multi-view data, and how to uncover its intrinsic structure and utilize it to conduct the subsequent downstream tasks is crucial in data analysis. Multi-view clustering is representative of handling multi-view data. The anchor-based method has received widespread attention for excellent performance and low time complexity. However, existing methods encounter two drawbacks, cutting down their performance, i.e., the assumption of the availability of all views and limited interaction of anchor generation among views. In some scenes, views arrive sequentially, and storing them is challenging owing to the limited space/privacy considerations, and the existing anchor-based MVC is unsuitable for this. Additionally, recent works fail to generate anchors with the guidance of other views, and it is tough to align the anchor graphs. To this end, we propose A Lightweight Anchor-Based Incremental Framework for Multi-view Clustering. Specifically, we first initialize an anchor graph with the assistance of k-means when a new view arrives. Then, the consensus one of the anchor graph is updated by the newly collected view with a permutation matrix. Our proposed method is more capable of anchor alignment because, in incremental MVC, the anchor graphs of previous views could be listed as a reference to guide the generation of anchor graphs of the coming view. Furthermore, we design a three-step iterative and convergent algorithm to address the resultant problem. Notably, the proposed algorithm shows outstanding effectiveness and time/space efficiency in extensive experiments.

Multi-view clustering, a pivotal technology in multimedia research, aims to leverage complementary information from diverse perspectives to enhance clustering performance. The current multi-view clustering methods normally enforce the reduction of distances between any pair of views, overlooking the heterogeneity between views, thereby sacrificing the diverse and valuable insights inherent in multi-view data. In this paper, we propose a Tree-Based View-Gap Maintaining Multi-View Clustering (TGM-MVC) method. Our approach introduces a novel conceptualization of multiple views as a graph structure. In this structure, each view corresponds to a node, with the view gap, calculated by the cosine distance between views, acting as the edge. Through graph pruning, we derive the minimum spanning tree of the views, reflecting the neighbouring relationships among them. Specifically, we applied a share-specific learning framework, and generate view trees for both view-shared and view-specific information. Concerning shared information, we only narrow the distance between adjacent views, while for specific information, we maintain the view gap between neighboring views. Theoretical analysis highlights the risks of eliminating the view gap, and comprehensive experiments validate the efficacy of our proposed TGM-MVC method.

Contrastive deep graph clustering (CDGC) leverages the power of contrastive learning to group nodes into different clusters. The quality of contrastive samples is crucial for achieving better performance, making augmentation techniques a key factor in the process. However, the augmentation samples in existing methods are always predefined by human experiences, and agnostic from the downstream task clustering, thus leading to high human resource costs and poor performance. To overcome these limitations, we propose a Graph Node Clustering with Fully Learnable Augmentation, termed GraphLearner. It introduces learnable augmentors to generate high-quality and task-specific augmented samples for CDGC. GraphLearner incorporates two learnable augmentors specifically designed for capturing attribute and structural information. Moreover, we introduce two refinement matrices, including the high-confidence pseudo-label matrix and the cross-view sample similarity matrix, to enhance the reliability of the learned affinity matrix. During the training procedure, we notice the distinct optimization goals for training learnable augmentors and contrastive learning networks. In other words, we should both guarantee the consistency of the embeddings as well as the diversity of the augmented samples. To address this challenge, we propose an adversarial learning mechanism within our method. Besides, we leverage a two-stage training strategy to refine the high-confidence matrices. Extensive experimental results on six benchmark datasets validate the effectiveness of GraphLearner.The code and appendix of GraphLearner are available at https://github.com/xihongyang1999/GraphLearner on Github.

Graph Neural Networks have demonstrated great success in various fields of multimedia. However, the distribution shift between the training and test data challenges the effectiveness of GNNs. To mitigate this challenge, Test-Time Training (TTT) has been proposed as a promising approach. Traditional TTT methods require a demanding unsupervised training strategy to capture the information from test to benefit the main task. Inspired by the great annotation ability of Large Language Models (LLMs) on Text-Attributed Graphs (TAGs), we propose to enhance the test-time training on graphs with LLMs as annotators. In this paper, we design a novel Test-Time Training pipeline, LLMTTT, which conducts the test-time adaptation under the annotations by LLMs on a carefully-selected node set. Specifically, LLMTTT introduces a hybrid active node selection strategy that considers not only node diversity and representativeness, but also prediction signals from the pre-trained model. Given annotations from LLMs, a two-stage training strategy is designed to tailor the test-time model with the limited and noisy labels. A theoretical analysis ensures the validity of our method and extensive experiments demonstrate that the proposed LLMTTT can achieve a significant performance improvement compared to existing Out-of-Distribution (OOD) generalization methods.

Traditional knowledge graph embedding (KGE) models map entities and relations to unique embedding vectors in a shallow lookup manner. As the scale of data becomes larger, this manner will raise unaffordable computational costs. Anchor-based strategies have been treated as effective ways to alleviate such efficiency problems by propagation on representative entities instead of the whole graph. However, most existing anchor-based KGE models select the anchors in a primitive manner, which limits their performance. To this end, we propose a novel anchor-based strategy for KGE, i.e., a relational clustering-based anchor selection strategy (RecPiece), where two characteristics are leveraged, i.e., (1) representative ability of the cluster centroids and (2) descriptive ability of relation types in KGs. Specifically, we first perform clustering over features of factual triplets instead of entities, where cluster number is naturally set as number of relation types since each fact can be characterized by its relation in KGs. Then, representative triplets are selected around the clustering centroids, further mapped into corresponding anchor entities. Extensive experiments on six datasets show that RecPiece achieves higher performances but comparable or even fewer parameters compared to previous anchor-based KGE models, indicating that our model can select better anchors in a more scalable way.

Incomplete multi-view clustering aims to learn complete correlations among samples by leveraging complementary information across multiple views for clustering. Anchor-based methods further establish sample-level similarities for representative anchor generation, effectively addressing scalability issues in large-scale scenarios. Despite efficiency improvements, existing methods overlook the misguidance in anchors learning induced by partial missing samples, i.e., the absence of samples results in shift of learned anchors, further leading to sub-optimal clustering performance. To conquer the challenges, our solution involves a cross-view reconstruction strategy that not only alleviate the anchor shift problem through a carefully designed cross-view learning process, but also reconstructs missing samples in a way that transcends the limitations imposed by convex combinations. By employing affine combinations, our method explores areas beyond the convex hull defined by anchors, thereby illuminating blind spots in the reconstruction of missing samples. Experimental results on four benchmark datasets and three large-scale datasets validate the effectiveness of our proposed method.

Intent learning, which aims to learn users' intents for user understanding and item recommendation, has become a hot research spot in recent years. However, existing methods suffer from complex and cumbersome alternating optimization, limiting performance and scalability. To this end, we propose a novel intent learning method termed \underline{ELCRec}, by unifying behavior representation learning into an \underline{E}nd-to-end \underline{L}earnable \underline{C}lustering framework, for effective and efficient \underline{Rec}ommendation. Concretely, we encode user behavior sequences and initialize the cluster centers (latent intents) as learnable neurons. Then, we design a novel learnable clustering module to separate different cluster centers, thus decoupling users' complex intents. Meanwhile, it guides the network to learn intents from behaviors by forcing behavior embeddings close to cluster centers. This allows simultaneous optimization of recommendation and clustering via mini-batch data. Moreover, we propose intent-assisted contrastive learning by using cluster centers as self-supervision signals, further enhancing mutual promotion. Both experimental results and theoretical analyses demonstrate the superiority of ELCRec from six perspectives. Compared to the runner-up, ELCRec improves NDCG@5 by 8.9\% and reduces computational costs by 22.5\% on the Beauty dataset. Furthermore, due to the scalability and universal applicability, we deploy this method on the industrial recommendation system with 130 million page views and achieve promising results. The codes are available on GitHub\footnote{https://github.com/yueliu1999/ELCRec}. A collection (papers, codes, datasets) of deep group recommendation/intent learning methods is available on GitHub\footnote{https://github.com/yueliu1999/Awesome-Deep-Group-Recommendation}.

The fundamental goal of deep multi-view clustering is to achieve preferable task performance through inter-view cooperation. Although numerous DMVC approaches have been proposed, the collaboration role of individual views have not been well investigated in existing literature. Moreover, how to further enhance view cooperation for better fusion still needs to be explored. In this paper, we firstly consider DMVC as an unsupervised cooperative game where each view can be regarded as a participant. Then, we introduce the Shapley value and propose a novel MVC framework termed Shapley-based Cooperation Enhancing Multi-view Clustering (SCE-MVC), which evaluates view cooperation with game theory. Specially, we employ the optimal transport distance between fused cluster distributions and single view component as the utility function for computing shapley values. Afterwards, we apply shapley values to assess the contribution of each view and utilize these contributions to promote view cooperation. Comprehensive experimental results well support the effectiveness of our framework adopting to existing DMVC frameworks, demonstrating the importance and necessity of enhancing the cooperation among views.

In recent years, there has been significant advancement in the field of single-cell data analysis, particularly in the development of clustering methods. Despite these advancements, most algorithms continue to focus primarily on analyzing the provided single-cell matrix data. However, within medical contexts, single-cell data often encompasses a wealth of exogenous information, such as gene networks. Overlooking this aspect could result in information loss and produce clustering outcomes lacking significant clinical relevance. To address this limitation, we introduce an innovative deep clustering method for single-cell data that leverages exogenous gene information to generate discriminative cell representations. Specifically, an attention-enhanced graph autoencoder has been developed to efficiently capture topological signal patterns among cells. Concurrently, a random walk on an exogenous protein-protein interaction network enabled the acquisition of the gene's embeddings. Ultimately, the clustering process entailed integrating and reconstructing gene-cell cooperative embeddings, which yielded a discriminative representation. Extensive experiments have demonstrated the effectiveness of the proposed method. This research provides enhanced insights into the characteristics of cells, thus laying the foundation for the early diagnosis and treatment of diseases. The datasets and code can be publicly accessed in the repository at https://github.com/DayuHuu/scEGG.

Unsupervised person reidentification (Re-ID) has attracted widespread due to its potential in Internet of Things applications, such as intelligent visual surveillance, it refers to retrieving the same individual across different camera views without using labeled data. To tackle the problem, a prevalent technique adopted by existing methods involves generating pseudo labels through clustering algorithms. However, this approach can result in merging individuals with different identities into the same group (i.e., cluster) during the training process. As a result, the resulting group centers may obscure the inherent characteristics of individual identities, thereby hindering the model from learning discriminative representations. To address the issue, we present a teacher-guided individual- and group-aware contrastive learning framework. Specifically, we propose a departure from the traditional approach of relying solely on contrastive learning between individual features and their corresponding group centers. Instead, we also exploit the relationship among individuals to construct contrast pairs and facilitate the learning of more discriminative features. This strategy enables the model to learn more about the individual characteristics that distinguish different persons, thus enhancing its ability to reidentify individuals accurately. Moreover, our method introduces a novel hybrid distillation module that enables simultaneous probability distillation at the group level and relationship distillation at the individual level. Guided by the teacher model, this module leads to improved feature representations of the student model. Extensive experimental results verify the effectiveness of our approach on four popular Re-ID data sets. The code will be made publicly available.

Knowledge graph reasoning (KGR), aiming to deduce new facts from existing facts based on mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research direction. It has been proven to significantly benefit the usage of KGs in many AI applications, such as question answering, recommendation systems, and etc. According to the graph types, existing KGR models can be roughly divided into three categories, i.e., static models, temporal models, and multi-modal models. Early works in this domain mainly focus on static KGR, and recent works try to leverage the temporal and multi-modal information, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for knowledge graph reasoning tracing from static to temporal and then to multi-modal KGs. Concretely, the models are reviewed based on bi-level taxonomy, i.e., top-level (graph types) and base-level (techniques and scenarios). Besides, the performances, as well as datasets, are summarized and presented. Moreover, we point out the challenges and potential opportunities to enlighten the readers.

Existing multiple kernel clustering (MKC) algorithms have two ubiquitous problems. From the theoretical perspective, most MKC algorithms lack sufficient theoretical analysis, especially the consistency of learned parameters, such as the kernel weights. From the practical perspective, the high complexity makes MKC unable to handle large-scale datasets. This paper tries to address the above two issues. We first make a consistency analysis of an influential MKC method named Simple Multiple Kernel$k$-Means (SimpleMKKM). Specifically, suppose that$\hat{\boldsymbol{\gamma }}_{n}$are the kernel weights learned by SimpleMKKM from the training samples. We also define the expected version of SimpleMKKM and denote its solution as$\boldsymbol{\gamma }^*$. We establish an upper bound of$\Vert \hat{\boldsymbol{\gamma }}_{n}-\boldsymbol{\gamma }^*\Vert _\infty$in the order of$\widetilde{\mathcal {O}}(1/\sqrt{n})$, where$n$is the sample number. Based on this result, we also derive its excess clustering risk calculated by a standard clustering loss function. For the large-scale extension, we replace the eigen decomposition of SimpleMKKM with singular value decomposition (SVD). Consequently, the complexity can be decreased to$\mathcal {O}(n)$such that SimpleMKKM can be implemented on large-scale datasets. We then deduce several theoretical results to verify the approximation ability of the proposed SVD-based method. The results of comprehensive experiments demonstrate the superiority of the proposed method. The code is publicly available athttps://github.com/weixuan-liang/SVD-based-SimpleMKKM.

Multiple kernel alignment (MKA) maximization criterion has been widely applied into multiple kernel clustering (MKC) and many variants have been recently developed. Though demonstrating superior clustering performance in various applications, it is observed that none of them can effectively handle incomplete MKC, where parts or all of the pre-specified base kernel matrices are incomplete. To address this issue, we propose to integrate the imputation of incomplete kernel matrices and MKA maximization for clustering into a unified learning framework. The clustering of MKA maximization guides the imputation of incomplete kernel elements, and the completed kernel matrices are in turn combined to conduct the subsequent MKC. These two procedures are alternately performed until convergence. By this way, the imputation and MKC processes are seamlessly connected, with the aim to achieve better clustering performance. Besides theoretically analyzing the clustering generalization error bound, we empirically evaluate the clustering performance on several multiple kernel learning (MKL) benchmark datasets, and the results indicate the superiority of our algorithm over existing state-of-the-art counterparts. Our codes and data are publicly available at https://xinwangliu.github.io/.

Deep neural network (DNN) intellectual property (IP) models must be kept undisclosed to avoid revealing trade secrets. Recent works have devised machine learning techniques that leverage on side-channel information leakage of the target platform to reverse engineer DNN architectures. However, these works fail to perform successful attacks on DNNs that have undergone performance optimizations (i.e., operator fusion) using DNN compilers, e.g., Apache tensor virtual machine (TVM). We propose a two-phase attack framework to infer the layer sequences of optimized DNNs through side-channel information leakage. In the first phase, we use a recurrent network with multihead attention components to learn the intra and interlayer fusion patterns from GPU traces of TVM-optimized DNNs, in order to accurately predict the operation distribution. The second phase uses a model to learn the run-time temporal correlations between operations and layers, which enables the prediction of layer sequence. An encoding strategy is proposed to overcome the convergence issues faced by existing learning-based methods when inferring the layer sequences of optimized DNNs. Extensive experiments show that our learning-based framework outperforms state-of-the-art DNN model extraction techniques. Our framework is also the first to effectively reverse engineer both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) using side-channel leakage.

Multi-view subspace clustering (MVSC) is a popular area of research that concentrates on partitioning data points from multiple views. It has gained wide attention in recent years due to the ability to handle complex data with diverse features across different views. However, the success of MVSC largely relies on the quality of the learned similarity matrix, and existing methods normally adopt the separate two-step procedures of optimization and symmetrization, which could not guarantee symmetry and adaptive locality of the similarity matrix. To alleviate this issue, in this paper, we propose a novel paradigm called Symmetric Multi-view Subspace Clustering with Automatic Neighbor Discovery (SMSC-AND), which aims at formulating the symmetrization and localization of the ideal similarity matrix into one unified framework. In particular, we theoretically and experimentally demonstrate that SMSC-AND can directly receive the refined symmetric similarity matrix without previous post-processing procedures. Additionally, we propose an automatic neighbor discovery strategy that avoids previous rank constraints or fixed neighbor size, thereby eliminating the requirement for additional hyperparameters. Benefiting from the aforementioned merits, we can directly explore the local structure of the consensus similarity matrix of multi-view data without pre-searching hyperparameters. Comprehensive experimental results on various benchmark datasets have demonstrated the superiority of the proposed algorithm when compared with other MVSC competitors.

Anchor based incomplete multiview clustering has grasped growing interest recently because of its great success in effectively partitioning multimodal data. However, due to the absence of label information, the constructed anchors could be mismatched. Such an Anchor Mismatching Problem (AMP) will cause the structure of generated bipartite graph to be chaotic, degrading the clustering performance. To tackle this issue, we design an algorithm termed Constructing Corresponding Anchors for Incomplete Multiview Clustering (CCA-IMC). Specifically, we first devise a permutation strategy to transform anchors on each view. Subsequently, we directly generate the consensus bipartite graph, which is shared for all incomplete views, by the transformed anchors rather than by fusing each view-specific bipartite graph. Afterwards, all anchors and permutation matrices as well as the consensus bipartite graph are jointly optimized in one common framework so as to promote each other. In such ways, anchors are rearranged towards correct matching relationship according to the consensus graph structure. In addition to these, our CCA-IMC has also been proven to be with linear time and memory overheads, which makes it able to scale up to work with large-scale tasks. Massive experiments implemented on ten popular datasets give evidence of our superiorities compared to current strong IMC competitors.

Incomplete multiview clustering (IMVC) generally requires the number of anchors to be the same in all views. Also, this number needs to be tuned with extra manual efforts. This not only degenerates the diversity of multiview data but also limits the model's scalability. For generating differentiated numbers of anchors without tuning, in this article we devise a novel framework named DAQINT. To be specific, the most perfect solution is to jointly find the optimal number of anchors that belongs to respective view. Regretfully, it is extremely time consuming. In view of this, we choose to first offer a set of anchor numbers for each view, and then integrate their contributions by adaptive weighting to approximate the optimal number. In particular, these offered numbers are all predefined and do not require any tuning. Through adaptively weighting them, we hold that this equivalently makes each view enjoy a different number of anchors. Accordingly, the bipartite graphs generated on all views are with diverse scales. Besides exploring multiview features more deeply, they also balance the importance between views. Then, to fuse these multiscale bipartite graphs, we design a combination strategy that owns linear computation and storage overheads. Afterward, to solve the resulting optimization problem, we also carefully develop a three-step iterative algorithm with linear complexities and demonstrated convergence. Experiments on the multiple public datasets validate the superiority of DAQINT against several advanced IMVC methods, such as on Mfeat, DAQINT surpasses the competitors like MKC, EEIMVC, FLSD, DSIMVC, IMVC-CBG, and DCP by 36.65%, 6.33%, 48.53%, 22.46%, 15.06%, and 32.04%, respectively, in ACC.

Single-cell multi-view clustering is essential for analyzing the different cell subtypes of the same cell from different views. Some attempts have been made, but most of these models still struggle to handle single-cell sequencing data, primarily due to their non-specific design for cellular data. We observe that such data distinctively exhibits: (1) a profusion of high-order topological correlations, (2) a disparate distribution of information across different views, and (3) inherent fuzzy characteristics, indicating a cell's potential to associate with multiple cluster identities. Neglecting these key cellular patterns could significantly impair medical clustering. In response, we propose a specialized application of fuzzy clustering for single-cell sequencing data, namely the deep Single-cell Multi-view Fuzzy Clustering (scMFC) method. Concretely, we employ a random walk technique to capture high-order topological relationships on the cell graph and have developed a cross-view information aggregation mechanism that adaptively assigns weights to different views. Furthermore, to accurately reflect the dynamic insight in cellular development, we propose a deep fuzzy clustering strategy that allows cells to associate with diverse clusters. Extensive experiments conducted on three real-world single-cell multi-view datasets demonstrate our method's superior performance.

Multi-view clustering has been received considerable attention due to the widespread collection of multi-view data from diverse domains and sources. However, storing multi-view data across multiple devices in many real scenarios poses significant challenges for efficient data analysis. Federated Learning framework enables collaborative machine learning on distributed devices while preserving privacy constraints. Even though there have been intensive algorithms on multi-view fuzzy clustering, federated multi-view fuzzy clustering has not been adequately investigated so far. In this study, we first develop the federated learning mode into multi-view fuzzy clustering and realize the federated optimization procedure, called Federated Multiview Fuzzy C-Means clustering (FedMVFCM). Then, we design an original strategy of consensus prototype learning during federated multi-view fuzzy clustering. It is termed as Federated Multi-view Fuzzy c-means consensus Prototypes Clustering (FedMVFPC). We also further develop the federated alternative optimization algorithm with proven convergence. This study also introduces the notion of clustering prototype communication within the federated learning framework, and integrates the clustering prototypes of different views into a unified optimization formulation. The experimental studies on various benchmark datasets demonstrate that the proposed FedMVFPC method improves the federated clustering performance and efficiency. It achieves comparable or better clustering performance against the existing state-of-the-art multi-view clustering algorithms

Hyperspectral image (HSI) clustering is a fundamental yet challenging task that groups image pixels with similar features into distinct clusters. Among various approaches, contrastive learning methods, which employ the concept of encouraging semantically similar samples to move closer together while pushing semantically inconsistent samples apart, have garnered significant attention due to their promising performance. However, the most prevalent approaches face two major limitations: 1) treating all samples indiscriminately during optimization, where the abundance of well-categorized samples overwhelms the feature learning process and 2) tending to introduce noise when constructing positive sample pairs through view augmentation or searching the nearest neighbors, which would cause semantic drift of sample features. To solve these issues, we propose a graph autoencoder-based deep clustering framework named spatial–spectral graph contrastive clustering with hard sample mining (SSGCC) that constructs spatial–spectral dual views without data augmentation and focuses more on hard samples rather than treating all samples equally with the aid of spatial–spectral features. Concretely, we extract the spectral features and the neighborhood spatial features of the samples as dual branches to avoid the noise caused by data augmentation and develop the cluster-oriented consistency learning to facilitate the exchange of knowledge between the two spectral–spatial perspectives. In addition, we propose a hard sample mining-based contrastive learning scheme with the aid of spatial–spectral features. To better measure the importance of the samples, we combine spatial features and spectral features to calculate the similarity between sample pairs. The weights of hard sample pairs are dynamically up-weight while the easy ones are down-weighting to improve the discriminative capability. Extensive experiments on four benchmark HSI datasets demonstrate the effectiveness and superiority of the proposed methods against state-of-the-art ones.

Fully supervised change detection methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information corresponding to both changed and unchanged objects in bi-temporal images, an intuitive solution is to segment the changes with patch-level annotations. How to capture the semantic variations associated with the changed and unchanged regions from the patch-level annotations to obtain promising change results is the critical challenge for the weakly supervised change detection task. In this paper, we propose a memory-supported transformer (MS-Former), a novel framework consisting of a bi-directional attention block (BAB) and a patch-level supervision scheme (PSS) tailored for weakly supervised change detection with patch-level annotations. More specifically, the BAB captures contexts associated with the changed and unchanged regions from the temporal difference features to construct informative prototypes stored in the memory bank. On the other hand, the BAB extracts useful information from the prototypes as supplementary contexts to enhance the temporal difference features, thereby better distinguishing changed and unchanged regions. After that, the PSS guides the network learning valuable knowledge from the patch-level annotations, thus further elevating the performance. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method in the change detection task. The demo code for our work will be publicly available at https://github.com/guanyuezhen/MS-Former.

Multi-view clustering (MVC) has attracted broad attention due to its capacity to exploit consistent and complementary information across views. This paper focuses on a challenging issue in MVC called the incomplete continual data problem (ICDP). Specifically, most existing algorithms assume that views are available in advance and overlook the scenarios where data observations of views are accumulated over time. Due to privacy considerations or memory limitations, previous views cannot be stored in these situations. Some works have proposed ways to handle this problem, but all of them fail to address incomplete views. Such an incomplete continual data problem (ICDP) in MVC is difficult to solve since incomplete information with continual data increases the difficulty of extracting consistent and complementary knowledge among views. We propose Fast Continual Multi-View Clustering with Incomplete Views (FCMVC-IV) to address this issue. Specifically, the method maintains a scalable consensus coefficient matrix and updates its knowledge with the incoming incomplete view rather than storing and recomputing all the data matrices. Considering that the given views are incomplete, the newly collected view might contain samples that have yet to appear; two indicator matrices and a rotation matrix are developed to match matrices with different dimensions. In addition, we design a three-step iterative algorithm to solve the resultant problem with linear complexity and proven convergence. Comprehensive experiments conducted on various datasets demonstrate the superiority of FCMVC-IV over the competing approaches. The code is publicly available at https://github.com/wanxinhang/FCMVC-IV.

Anchor graph has been recently proposed to accelerate multi-view graph clustering and widely applied in various large-scale applications. Different from capturing full instance relationships, these methods choose small portion anchors among each view, construct single-view anchor graphs and combine them into the unified graph. Despite its efficiency, we observe that: (i) Existing mechanism adopts a separable two-step procedure-anchor graph construction and individual graph fusion, which may degrade the clustering performance. (ii)These methods determine the number of selected anchors to be equal among all the views, which may destruct the data distribution diversity. A more flexible multi-view anchor graph fusion framework with diverse magnitudes is desired to enhance the representation ability. (iii) During the latter fusion process, current anchor graph fusion framework follows simple linearly-combined style while the intrinsic clustering structures are ignored. To address these issues, we propose a novel scalable and flexible anchor graph fusion framework for multi-view graph clustering method in this paper. Specially, the anchor graph construction and graph alignment are jointly optimized in our unified framework to boost clustering quality. Moreover, we present a novel structural alignment regularization to adaptively fuse multiple anchor graphs with different magnitudes. In addition, our proposed method inherits the linear complexity of existing anchor strategies respecting to the sample number, which is time-economical for large-scale data. Experiments conducted on various benchmark datasets demonstrate the superiority and effectiveness of the newly proposed anchor graph fusion framework against the existing state-of-the-arts over the clustering performance promotion and time expenditure. Our code is publicly available at https://github.com/wangsiwei2010/SMVAGC-SF.

Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years. However, the problem of insufficient supervision, together with representation collapse, largely limits the performance of the GNNs in this field. To alleviate the collapse of node representations in semi-supervised scenario, we propose a novel graph contrastive learning method, termed M ixed G raph C ontrastive N etwork (MGCN). In our method, we improve the discriminative capability of the latent embeddings by an interpolation-based augmentation strategy and a correlation reduction mechanism. Specifically, we first conduct the interpolation-based augmentation in the latent space and then force the prediction model to change linearly between samples. Second, we enable the learned network to tell apart samples across two interpolation-perturbed views through forcing the correlation matrix across views to approximate an identity matrix. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discriminative representation learning. Extensive experimental results on six datasets demonstrate the effectiveness and the generality of MGCN compared to the existing state-of-the-art methods. The code of MGCN is available at https://github.com/xihongyang1999/MGCN on Github.

Unsupervised multi-view bipartite graph clustering (MVBGC) is a fast-growing research, due to promising scalability in large-scale tasks. Although many variants are proposed by various strategies, a common design is to construct the bipartite graph directly from the input data, i.e. only consider the unidirectional “encoding” process. However, “encoding-decoding” mechanism is a popular design for deep learning, the most representative one is auto-encoder (AE). Enlightened by this, this paper rethinks existing MVBGC paradigms and transfers the “encoding-decoding” design into graph machine learning, and proposes a novel framework termed auto-encoding multi-view bipartite graph clustering (BGAE), which integrates encoding, bipartite graph construction, and decoding modules in a self-supervised learning manner. The encoding module extracts a latent joint representation from the input data, the bipartite graph construction module learns a bipartite graph with connectivity constraint in latent semantic space, and the decoding module recreates the input data via the bipartite graph. Therefore, our novel BGAE combines representation learning, bipartite graph learning, reconstruction learning, and label inference into a unified framework. All the modules are seamlessly integrated and mutually reinforcing for clustering-friendly purposes. Extensive experiments verify the superiority of our novel design and the significance of “decoding” process. To the best of our knowledge, this is the first attempt to explore “encoding-decoding” design in traditional MVBGC. The code is provided athttps://github.com/liliangnudt/BGAE.

Knowledge graph embedding (KGE) aims at learning powerful representations to benefit various artificial intelligence applications. Meanwhile, contrastive learning has been widely leveraged in graph learning as an effective mechanism to enhance the discriminative capacity of the learned representations. However, the complex structures of KG make it hard to construct appropriate contrastive pairs. Only a few attempts have integrated contrastive learning strategies with KGE. But, most of them rely on language models (e.g.,Bert) for contrastive pair construction instead of fully mining information underlying the graph structure, hindering expressive ability. Surprisingly, we find that the entities within a relational symmetrical structure are usually similar and correlated. To this end, we propose a knowledge graph contrastive learning framework based on relation-symmetrical structure, KGE-SymCL, which mines symmetrical structure information in KGs to enhance the discriminative ability of KGE models. Concretely, a plug-and-play approach is proposed by taking entities in the relation-symmetrical positions as positive pairs. Besides, a self-supervised alignment loss is designed to pull together positive pairs. Experimental results on link prediction and entity classification datasets demonstrate that our KGE-SymCL can be easily adopted to various KGE models for performance improvements. Moreover, extensive experiments show that our model could outperform other state-of-the-art baselines.

Anchor-based multi-view graph clustering has recently gained popularity as an effective approach for clustering data with multiple views. However, existing methods have limitations in terms of handling inconsistent information and noise across views, resulting in an unreliable consensus representation. Additionally, post-processing is needed to obtain final results after anchor graph construction, which negatively affects clustering performance. In this paper, we propose a Robust and Consistent Anchor Graph Learning method (RCAGL) for multi-view clustering to address these challenges. RCAGL constructs a consistent anchor graph that captures inter-view commonality and filters out view-specific noise by learning a consistent part and a view-specific part simultaneously. A$k$-connectivity constraint is imposed on the consistent anchor graph, leading to a clear graph structure and direct generation of cluster labels without additional post-processing. Experimental results on several benchmark datasets demonstrate the superiority of RCAGL in terms of clustering accuracy, scalability to large-scale data, and robustness to view-specific noise, outperforming advanced multi-view clustering methods. Our code is publicly available athttps://github.com/Tracesource/RCAGL.

Federated knowledge graph reasoning (FedKGR) aims to perform reasoning over different clients while protecting data privacy, drawing increasing attention to its high practical value. Previous works primarily focus on data heterogeneity, ignoring challenges from limited data scale and primitive negative sample strategies, i.e., random entity replacement, which yield low-quality negatives and zero loss issues. Meanwhile, generative adversarial networks (GANs) are widely used in different fields to generate high-quality negative samples, but no work has been developed for FedKGR. To this end, we propose a plug-and-playEntity-awareAdversarialNegative sampling strategy for FedKGR, termed FedEAN. Specifically, we are the first to adopt GANs to generate high-quality negative samples in different clients. It takes the target triplet in each batch as input and outputs high-quality negative samples, which guaranteed by the joint training of the generator and discriminator. Moreover, we design an entity-aware adaptive negative sampling mechanism based on the similarity of entity representations before and after server aggregation, which can persevere the entity global consistency across clients during training. Extensive experiments demonstrate that FedEAN excels with various FedKGR backbones, demonstrating its ability to construct high-quality negative samples and address the zero-loss issue.

Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important non-Euclidean property of graph data. As a result, the highly unstable local structures largely increase the uncertainty in inferring masked data and decrease the reliability of the exploited self-supervision signals, leading to inferior representations for downstream evaluations. To address this issue, we propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space. Through both theoretical and empirical analyses, we have discovered that performing a joint mask-then-reconstruct strategy in both latent feature and raw data spaces could yield improved stability and performance. To this end, we elaborately design a masked latent feature completion scheme, which predicts latent features of masked nodes under the guidance of high-order sample correlations that are hard to be observed from the raw data perspective. Specifically, we first adopt a latent feature predictor to predict the masked latent features from the visible ones. Next, we encode the raw data of masked samples with a momentum graph encoder and subsequently employ the resulting representations to improve the predicted results through latent feature matching. Extensive experiments on seventeen datasets have demonstrated the effectiveness and robustness of RARE against state-of-the-art (SOTA) competitors across three downstream tasks. Our source code is available athttps://github.com/WxTu/RARE.

Multiple kernel clustering (MKC) enhances clustering performance by deriving a consensus partition or graph from a predefined set of kernels. Despite many advanced MKC methods proposed in recent years, the prevalent approaches involve incorporating all kernels by default to capture diverse information within the data. However, learning from all kernels may not be better than one of a few kernels, particularly since some kernels exhibit a higher proportion of noise than semantic content. Additionally, existing MKC methods, whether based on early-fusion or late-fusion approaches, predominantly rely on pairwise relationships among samples or cluster structures, neglecting potential correlations between these two aspects. To this end, we propose a multiple kernel clustering with an adaptive multi-scale partition selection method (MPS), which exploits multiple-dimensional representations and the pairwise cluster structure for clustering. By the proposed kernel selection framework, potentially harmful kernels are dynamically excluded during the kernel fusion process, and then the multi-scale partitions and similarity graphs derived from the retained kernels are utilized to facilitate the improved consensus partition generation. Finally, extensive experiments are conducted to demonstrate the effectiveness of MPS on eight benchmark datasets.

Multiple Kernel Clustering (MKC) has emerged as a prominent research domain in recent decades due to its capacity to exploit diverse information from multiple views by learning an optimal kernel. Despite the successes achieved by various MKC methods, a significant challenge lies in the computational complexity associated with generating a consensus partition from the optimal kernel matrix, typically of size$n \times n$, where$n$represents the number of samples. This computational bottleneck restricts the practical applicability of these methods when confronted with large-scale datasets. Furthermore, certain existing MKC algorithms derive the consensus partition matrix by fusing all base partitions. However, this fusion process may inadvertently overlook critical information embedded in individual base kernels, potentially leading to inferior clustering performance. In light of these challenges, we introduce an innovative and efficient multiple kernel$k$-means approach, denoted as FAMKKM. Notably, FAMKKM incorporates two approximated partition matrices instead of the original individual partition matric for each base kernel. This strategic substitution significantly reduces computational complexity. Additionally, FAMKKM leverages the original kernel information to guide the fusion of all base partitions, thereby enhancing the quality of the resulting consensus partition matrix. Finally, we substantiate the efficacy and efficiency of the proposed FAMKKM through extensive experiments conducted on six benchmark datasets. Our results demonstrate its superiority over state-of-the-art methods. The demo code of this work is publicly available athttps://github.com/WangJun2023/FAMKKM

Multiple kernel clustering (MKC) aims to extract and integrate the clustering information from a set of pre-defined kernels for handling data which cannot be linearly separated well. More precisely, existing MKC methods generally devote to learn the complementary information from a set of kernel partitions, whose feature dimensions are commonly fixed as the upper bound$n$or lower bound$c$, where$n$and$c$represents the number of samples and clusters, respectively. However, the adopting of the lower bound or upper bound generally leads to poor clustering performance caused by the lack or redundancy of clustering information carried by kernel partitions. To tackle this issue, we propose a novel late fusion multiple kernel clustering method, termed as Eigenvalue Ratio Inspired Partition Learning and Fusion for Multiple Kernel Clustering (ERMKC), in this paper. Specifically, we propose an eigenvalue ratio based criterion to guide the kernel partition learning for each single kernel matrix, which ensures more suitable feature dimensions for the learnt kernel partitions. In addition, we also propose a novel late fusion model for fusing the learnt kernel partitions optimally. Furthermore, we conduct extensive experiments on numerous benchmark datasets to evaluate the proposed ERMKC method, whose results verify the effectiveness and advantage of the proposed method compared to the other state-of-the-art methods.

This study is devoted to the design of gradient boosted fuzzy rule-based models for regression problems. Fuzzy rule-based models are built on the basis of information granules formed in the input and output spaces whose structure involves a family of conditional ‘if-then’ statements. The architecture of fuzzy rule-based models contributes to the realization of a sound tradeoff between modeling accuracy and interpretability and computing overhead. Gradient boosting paradigm has emerged as a powerful learning method realized through sequentially fitting additive base learners to current residuals in the steepest descent way. However, surprisingly, studies on the design and analysis of gradient boosted fuzzy rule-based models are still lacking. In this study, fuzzy rule-based model is regarded as a base learner. Different loss functions and their influence on the performance of the final models are explored. We also thoroughly investigate an impact of the initial quality of the rule-based model (implied by the number of rules) on the process of gradient boosting. The performance of the proposed approach is illustrated by a series of experimental studies concerning synthetic and publicly available datasets.

Clustering ensemble often provides robust and stable results without accessing original features of data, and thus has been widely studied. The conventional clustering ensemble methods often take the full multiple base partitions as inputs and provide a consensus clustering result. However, in many real-world applications, full base partitions are hard to obtain because some data may be missing in some base partitions. To tackle this problem, in this paper, we propose a novel partial clustering ensemble method, which takes the partial multiple base partitions as inputs. In this method, we simultaneously fill the missing values in the base partitions and ensemble them by fully considering the consensus and diversity. Moreover, to address the unreliability issue in the partial data scenario, we seamlessly plug it into a self-paced learning framework. The extensive experiments on benchmark data sets demonstrate the effectiveness and efficiency of the proposed method when handling incomplete data.

Spatial transcriptomics technology fully leverages spatial location and gene expression information for spatial clustering tasks. However, existing spatial clustering methods primarily concentrate on utilizing the complementary features between spatial and gene expression information, while overlooking the discriminative features during the integration process. Consequently, the discriminative capability of node representation in the gene expression features is limited. Besides, most existing methods lack a flexible combination mechanism to adaptively integrate spatial and gene expression information. To this end, we propose an end-to-end deep learning method named MAFN for spatially resolved transcriptomics data clustering via a multi-view adaptive fusion network. Specifically, we first adaptively learn inter-view complementary features from spatial and gene expression information. To improve the discriminative capability of gene expression nodes by utilizing spatial information, we employ two GCN encoders to learn intra-view specific features and design a Cross-view Correlation Reduction (CCR) strategy to filter the irrelevant information. Moreover, considering the distinct characteristics of each view, a Cross-view Attention Module (CAM) is utilized to adaptively fuse the multi-view features. Extensive experimental results demonstrate that the proposed MAFN achieves competitive performance in spatial domain identification compared to other state-of-the-art ones.

Multiview clustering has attracted increasing attention to automatically divide instances into various groups without manual annotations. Traditional shadow methods discover the internal structure of data, while deep multiview clustering (DMVC) utilizes neural networks with clustering-friendly data embeddings. Although both of them achieve impressive performance in practical applications, we find that the former heavily relies on the quality of raw features, while the latter ignores the structure information of data. To address the above issue, we propose a novel method termed iterative deep structural graph contrast clustering (IDSGCC) for multiview raw data consisting of topology learning (TL), representation learning (RL), and graph structure contrastive learning to achieve better performance. The TL module aims to obtain a structured global graph with constraint structural information and then guides the RL to preserve the structural information. In the RL module, graph convolutional network (GCN) takes the global structural graph and raw features as inputs to aggregate the samples of the same cluster and keep the samples of different clusters away. Unlike previous methods performing contrastive learning at the representation level of the samples, in the graph contrastive learning module, we conduct contrastive learning at the graph structure level by imposing a regularization term on the similarity matrix. The credible neighbors of the samples are constructed as positive pairs through the credible graph, and other samples are constructed as negative pairs. The three modules promote each other and finally obtain clustering-friendly embedding. Also, we set up an iterative update mechanism to update the topology to obtain a more credible topology. Impressive clustering results are obtained through the iterative mechanism. Comparative experiments on eight multiview datasets show that our model outperforms the state-of-the-art traditional and deep clustering competitors.

Recently, graph anomaly detection on attributed networks has attracted growing attention in data mining and machine learning communities. Apart from attribute anomalies, graph anomaly detection also aims at suspicious topological-abnormal nodes that exhibit collective anomalous behavior. Closely connected uncorrelated node groups form uncommonly dense substructures in the network. However, existing methods overlook that the topology anomaly detection performance can be improved by recognizing such a collective pattern. To this end, we propose a new graph anomaly detection framework on attributed networks via substructure awareness (ARISE). Unlike previous algorithms, we focus on the substructures in the graph to discern abnormalities. Specifically, we establish a region proposal module to discover high-density substructures in the network as suspicious regions. The average node-pair similarity can be regarded as the topology anomaly degree of nodes within substructures. Generally, the lower the similarity, the higher the probability that internal nodes are topology anomalies. To distill better embeddings of node attributes, we further introduce a graph contrastive learning scheme, which observes attribute anomalies in the meantime. In this way, ARISE can detect both topology and attribute anomalies. Ultimately, extensive experiments on benchmark datasets show that ARISE greatly improves detection performance (up to 7.30% AUC and 17.46% AUPRC gains) compared to state-of-the-art attributed networks anomaly detection (ANAD) algorithms.

Deep clustering, which can elegantly exploit data representation to seek a partition of the samples, has attracted intensive attention. Recently, combining auto-encoder (AE) with graph neural networks (GNNs) has accomplished excellent performance by introducing structural information implied among data in clustering tasks. However, we observe that there are some limitations of most existing works: 1) in practical graph datasets, there exist some noisy or inaccurate connections among nodes, which would confuse network learning and cause biased representations, thus leading to unsatisfied clustering performance; 2) lacking dynamic information fusion module to carefully combine and refine the node attributes and the graph structural information to learn more consistent representations; and 3) failing to exploit the two separated views' information for generating a more robust target distribution. To solve these problems, we propose a novel method termed deep fusion clustering network with reliable structure preservation (DFCN-RSP). Specifically, the random walk mechanism is introduced to boost the reliability of the original graph structure by measuring localized structure similarities among nodes. It can simultaneously filter out noisy connections and supplement reliable connections in the original graph. Moreover, we provide a transformer-based graph auto-encoder (TGAE) that can use a self-attention mechanism with the localized structure similarity information to fine-tune the fused topology structure among nodes layer by layer. Furthermore, we provide a dynamic cross-modality fusion strategy to combine the representations learned from both TGAE and AE. Also, we design a triplet self-supervision strategy and a target distribution generation measure to explore the cross-modality information. The experimental results on five public benchmark datasets reflect that DFCN-RSP is more competitive than the state-of-the-art deep clustering algorithms. The corresponding code is available at https://github.com/gongleii/DFCN-RSP.

Multiview clustering (MVC) sufficiently exploits the diverse and complementary information among different views to improve the clustering performance. As a representative algorithm of MVC, the newly proposed simple multiple kernel k -means (SimpleMKKM) algorithm takes a min-max formulation and applies a gradient descent algorithm to decrease the resultant objective function. It is empirically observed that its superiority is attributed to the novel min-max formulation and the new optimization. In this article, we propose to integrate the min-max learning paradigm adopted by SimpleMKKM into late fusion MVC (LF-MVC). This leads to a tri-level max-min-max optimization problem with respect to the perturbation matrices, weight coefficient, and clustering partition matrix. To solve this intractable max-min-max optimization problem, we design an efficient two-step alternative optimization strategy. Furthermore, we analyze the generalization clustering performance of the proposed algorithm from the theoretical perspective. Comprehensive experiments have been conducted to evaluate the proposed algorithm in terms of clustering accuracy (ACC), computation time, convergence, as well as the evolution of the learned consensus clustering matrix, clustering with different numbers of samples, and analysis of the learned kernel weight. The experimental results show that the proposed algorithm is able to significantly reduce the computation time and improve the clustering ACC when compared to several state-of-the-art LF-MVC algorithms. The code of this work is publicly released at: https://xinwangliu.github.io/Under-Review.

Multiview clustering (MVC) seamlessly combines homogeneous information and allocates data samples into different communities, which has shown significant effectiveness for unsupervised tasks in recent years. However, some views of samples may be incomplete due to unfinished data collection or storage failure in reality, which refers to the so-called incomplete multiview clustering (IMVC). Despite many IMVC pioneer frameworks have been introduced, the majority of their approaches are limited by the cubic time complexity and quadratic space complexity which heavily prevent them from being employed in large-scale IMVC tasks. Moreover, the massively introduced hyper-parameters in existing methods are not practical in real applications. Inspired by recent unsupervised multiview prototype progress, we propose a novel parameter-free and scalable incomplete multiview clustering framework with the prototype graph termed PSIMVC-PG to solve the aforementioned issues. Different from existing full pair-wise graph studying, we construct an incomplete prototype graph to flexibly capture the relations between existing instances and discriminate prototypes. Moreover, PSIMVC-PG can directly obtain the prototype graph without pre-process of searching hyper-parameters. We conduct massive experiments on various incomplete multiview tasks, and the performances show clear advantages over existing methods. The code of PSIMVC-PG can be publicly downloaded at https://github.com/wangsiwei2010/PSIMVC-PG.

Multiple kernel clustering (MKC) is committed to achieving optimal information fusion from a set of base kernels. Constructing precise and local kernel matrices is proven to be of vital significance in applications since the unreliable distant-distance similarity estimation would degrade clustering performance. Although existing localized MKC algorithms exhibit improved performance compared with globally designed competitors, most of them widely adopt the KNN mechanism to localize kernel matrix by accounting for τ -nearest neighbors. However, such a coarse manner follows an unreasonable strategy that the ranking importance of different neighbors is equal, which is impractical in applications. To alleviate such problems, this article proposes a novel local sample-weighted MKC (LSWMKC) model. We first construct a consensus discriminative affinity graph in kernel space, revealing the latent local structures. Furthermore, an optimal neighborhood kernel for the learned affinity graph is output with naturally sparse property and clear block diagonal structure. Moreover, LSWMKC implicitly optimizes adaptive weights on different neighbors with corresponding samples. Experimental results demonstrate that our LSWMKC possesses better local manifold representation and outperforms existing kernel or graph-based clustering algorithms. The source code of LSWMKC can be publicly accessed from https://github.com/liliangnudt/LSWMKC.

Multiple kernel clustering (MKC) aims to learn an optimal kernel to better serve for clustering from several precomputed basic kernels. Most MKC algorithms adhere to a common assumption that an optimal kernel is linearly combined by basic kernels. Based on a min-max framework, a newly proposed MKC method termed simple multiple kernel k -means (SimpleMKKM) can acquire a high-quality unified kernel. Although SimpleMKKM has achieved promising clustering performance, we observe that it cannot benefit from any prior knowledge. This would cause the learned partition matrix may seriously deviate from the expected one, especially in clustering tasks where the ground truth is absent during the learning course. To tackle this issue, we propose a novel algorithm termed regularized simple multiple kernel k -means with kernel average alignment (R-SMKKM-KAA). According to the experimental results of existing MKC algorithms, the average partition is a strong baseline to reflect true clustering. To gain knowledge from the average partition, we add the average alignment as a regularization term to prevent the learned unified partition from being far from the average partition. After that, we have designed an efficient solving algorithm to optimize the new resulting problem. In this way, both the incorporated prior knowledge and the combination of basic kernels are helpful to learn better unified partition. Consequently, the clustering performance can be significantly improved. Extensive experiments on nine common datasets have sufficiently demonstrated the effectiveness of incorporation of prior knowledge into SimpleMKKM.

Multi-view clustering (MVC) methods aim to exploit consistent and complementary information among each view and achieve encouraging performance improvement than single-view counterparts. In practical applications, it is common to obtain instances with partially available information, raising researches of incomplete multi-view clustering (IMC) issues. Recently, several fast IMC methods have been proposed to process the large-scale partial data. Though with considerable acceleration, these methods seek view-shared anchors and ignore specific information among single views. To tackle the above issue, we propose a fast IMC with view-independent anchors (FIMVC-VIA) method in this article. Specifically, we learn individual anchors based on the diversity of distribution among each incomplete view and construct a unified anchor graph following the principle of consistent clustering structure. By constructing an anchor graph instead of pairwise full graph, the time and space complexities of our proposed FIMVC-VIA are proven to be linearly related to the number of samples, which can efficiently solve the large-scale task. The experiment performed on benchmarks with different missing rate illustrates the improvement in complexity and effectiveness of our method compared with other IMC methods. Our code is publicly available at https://github.com/Tracesource/ FIMVC-VIA.

Contrastive learning has recently attracted plenty of attention in deep graph clustering due to its promising performance. However, complicated data augmentations and time-consuming graph convolutional operations undermine the efficiency of these methods. To solve this problem, we propose a simple contrastive graph clustering (SCGC) algorithm to improve the existing methods from the perspectives of network architecture, data augmentation, and objective function. As to the architecture, our network includes two main parts, that is, preprocessing and network backbone. A simple low-pass denoising operation conducts neighbor information aggregation as an independent preprocessing, and only two multilayer perceptrons (MLPs) are included as the backbone. For data augmentation, instead of introducing complex operations over graphs, we construct two augmented views of the same vertex by designing parameter unshared Siamese encoders and perturbing the node embeddings directly. Finally, as to the objective function, to further improve the clustering performance, a novel cross-view structural consistency objective function is designed to enhance the discriminative capability of the learned network. Extensive experimental results on seven benchmark datasets validate our proposed algorithm's effectiveness and superiority. Significantly, our algorithm outperforms the recent contrastive deep clustering competitors with at least seven times speedup on average. The code of SCGC is released at SCGC. Besides, we share a collection of deep graph clustering, including papers, codes, and datasets at ADGC.

Multiview spectral clustering, renowned for its spatial learning capability, has garnered significant attention in the data mining field. However, existing methods assume that the optimal consensus adjacency matrix is confined within the space spanned by each view's adjacency matrix. This constraint restricts the feasible domain of the algorithm and hinders the exploration of the optimal consensus adjacency matrix. To address this limitation, we propose a novel and convex strategy, termed the consensus neighbor strategy, for learning the optimal consensus adjacency matrix. This approach constructs the optimal consensus adjacency matrix by capturing the consensus local structure of each sample across all views, thereby expanding the search space and facilitating the discovery of the optimal consensus adjacency matrix. Furthermore, we introduce the concept of a correlation measuring matrix to prevent trivial solution. We develop an efficient iterative algorithm to solve the resulting optimization problem, benefitting from the convex nature of our model, which ensures convergence to a global optimum. Experimental results on 16 multiview datasets demonstrate that our proposed algorithm surpasses state-of-the-art methods in terms of its robust consensus representation learning capability. The code of this article is uploaded to https://github.com/PhdJiayiTang/Consensus-Neighbor-Strategy.git.

Contrastive learning has recently emerged as a powerful technique for graph self-supervised pretraining (GSP). By maximizing the mutual information (MI) between a positive sample pair, the network is forced to extract discriminative information from graphs to generate high-quality sample representations. However, we observe that, in the process of MI maximization (Infomax), the existing contrastive GSP algorithms suffer from at least one of the following problems: 1) treat all samples equally during optimization and 2) fall into a single contrasting pattern within the graph. Consequently, the vast number of well-categorized samples overwhelms the representation learning process, and limited information is accumulated, thus deteriorating the learning capability of the network. To solve these issues, in this article, by fusing the information from different views and conducting hard sample mining in a hierarchically contrastive manner, we propose a novel GSP algorithm called hierarchically contrastive hard sample mining (HCHSM). The hierarchical property of this algorithm is manifested in two aspects. First, according to the results of multilevel MI estimation in different views, the MI-based hard sample selection (MHSS) module keeps filtering the easy nodes and drives the network to focus more on hard nodes. Second, to collect more comprehensive information for hard sample learning, we introduce a hierarchically contrastive scheme to sequentially force the learned node representations to involve multilevel intrinsic graph features. In this way, as the contrastive granularity goes finer, the complementary information from different levels can be uniformly encoded to boost the discrimination of hard samples and enhance the quality of the learned graph embedding. Extensive experiments on seven benchmark datasets indicate that the HCHSM performs better than other competitors on node classification and node clustering tasks. The source code of HCHSM is available at https://github.com/WxTu/HCHSM.

Anomaly detection (AD), which models a given normal class and distinguishes it from the rest of abnormal classes, has been a long-standing topic with ubiquitous applications. As modern scenarios often deal with massive high-dimensional complex data spawned by multiple sources, it is natural to consider AD from the perspective of multiview deep learning. However, it has not been formally discussed by the literature and remains underexplored. Motivated by this blank, this article makes fourfold contributions: First, to the best of our knowledge, this is the first work that formally identifies and formulates the multiview deep AD problem. Second, we take recent advances in relevant areas into account and systematically devise various baseline solutions, which lays the foundation for multiview deep AD research. Third, to remedy the problem that limited benchmark datasets are available for multiview deep AD, we extensively collect the existing public data and process them into more than 30 multiview benchmark datasets via multiple means, so as to provide a better evaluation platform for multiview deep AD. Finally, by comprehensively evaluating the devised solutions on different types of multiview deep AD benchmark datasets, we conduct a thorough analysis on the effectiveness of the designed baselines and hopefully provide other researchers with beneficial guidance and insight into the new multiview deep AD topic.

Multi-view clustering (MVC), which effectively fuses information from multiple views for better performance, has received increasing attention. Most existing MVC methods assume that multi-view data are fully paired, which means that the mappings of all corresponding samples between views are predefined or given in advance. However, the data correspondence is often incomplete in real-world applications due to data corruption or sensor differences, referred to as the data-unpaired problem (DUP) in multi-view literature. Although several attempts have been made to address the DUP issue, they suffer from the following drawbacks: 1) most methods focus on the feature representation while ignoring the structural information of multi-view data, which is essential for clustering tasks; 2) existing methods for partially unpaired problems rely on pregiven cross-view alignment information, resulting in their inability to handle fully unpaired problems; and 3) their inevitable parameters degrade the efficiency and applicability of the models. To tackle these issues, we propose a novel parameter-free graph clustering framework termed unpaired multi-view graph clustering framework with cross-view structure matching (UPMGC-SM). Specifically, unlike the existing methods, UPMGC-SM effectively utilizes the structural information from each view to refine cross-view correspondences. Besides, our UPMGC-SM is a unified framework for both the fully and partially unpaired multi-view graph clustering. Moreover, existing graph clustering methods can adopt our UPMGC-SM to enhance their ability for unpaired scenarios. Extensive experiments demonstrate the effectiveness and generalization of our proposed framework for both paired and unpaired datasets.

Semi-supervised learning (SSL) has long been proved to be an effective technique to construct powerful models with limited labels. In the existing literature, consistency regularization-based methods, which force the perturbed samples to have similar predictions with the original ones have attracted much attention for their promising accuracy. However, we observe that the performance of such methods decreases drastically when the labels get extremely limited, e.g., 2 or 3 labels for each category. Our empirical study finds that the main problem lies with the drift of semantic information in the procedure of data augmentation. The problem can be alleviated when enough supervision is provided. However, when little guidance is available, the incorrect regularization would mislead the network and undermine the performance of the algorithm. To tackle the problem, we: 1) propose an interpolation-based method to construct more reliable positive sample pairs and 2) design a novel contrastive loss to guide the embedding of the learned network to change linearly between samples so as to improve the discriminative capability of the network by enlarging the margin decision boundaries. Since no destructive regularization is introduced, the performance of our proposed algorithm is largely improved. Specifically, the proposed algorithm outperforms the second best algorithm (Comatch) with 5.3% by achieving 88.73% classification accuracy when only two labels are available for each class on the CIFAR-10 dataset. Moreover, we further prove the generality of the proposed method by improving the performance of the existing state-of-the-art algorithms considerably with our proposed strategy. The corresponding code is available at https://github.com/xihongyang1999/ICL_SSL.

A weakness of the existing metric-based few-shot classification method is that task-unrelated objects or backgrounds may mislead the model since the small number of samples in the support set is insufficient to reveal the task-related targets. An essential cue of human wisdom in the few-shot classification task is that they can recognize the task-related targets by a glimpse of support images without being distracted by task-unrelated things. Thus, we propose to explicitly learn task-related saliency features and make use of them in the metric-based few-shot learning schema. We divide the tackling of the task into three phases, namely, the modeling, the analyzing, and the matching. In the modeling phase, we introduce a saliency sensitive module (SSM), which is an inexact supervision task jointly trained with a standard multiclass classification task. SSM not only enhances the fine-grained representation of feature embedding but also can locate the task-related saliency features. Meanwhile, we propose a self-training-based task-related saliency network (TRSN) which is a lightweight network to distill task-related salience produced by SSM. In the analyzing phase, we freeze TRSN and use it to handle novel tasks. TRSN extracts task-relevant features while suppressing the disturbing task-unrelated features. We, therefore, can discriminate samples accurately in the matching phase by strengthening the task-related features. We conduct extensive experiments on five-way 1-shot and 5-shot settings to evaluate the proposed method. Results show that our method achieves a consistent performance gain on benchmarks and achieves the state-of-the-art.

A clustering ensemble provides an elegant framework to learn a consensus result from multiple prespecified clustering partitions. Though conventional clustering ensemble methods achieve promising performance in various applications, we observe that they may usually be misled by some unreliable instances due to the absence of labels. To tackle this issue, we propose a novel active clustering ensemble method, which selects the uncertain or unreliable data for querying the annotations in the process of the ensemble. To fulfill this idea, we seamlessly integrate the active clustering ensemble method into a self-paced learning framework, leading to a novel self-paced active clustering ensemble (SPACE) method. The proposed SPACE can jointly select unreliable data to label via automatically evaluating their difficulty and applying easy data to ensemble the clusterings. In this way, these two tasks can be boosted by each other, with the aim to achieve better clustering performance. The experimental results on benchmark datasets demonstrate the significant effectiveness of our method. The codes of this article are released in https://Doctor-Nobody.github.io/codes/space.zip.

Few-shot learning presents a substantial challenge in developing robust models due to the inherent scarcity of samples within each category. To overcome this challenge, metric-based methods have been introduced, classifying images based on the relationships among samples within a given embedding space. While these methods are effective, the limited samples often result in an incomplete representation of the category’s feature space, leading to sub-optimal prototypes for classification. Recognizing this shortcoming, we identified that categories in new tasks often exhibit structural similarities with those in the relative base domain. Driven by this observation, we introduce ProtoRefine. Our approach employs the structural information of categories within the base domain that bear relevance to the new tasks, generating additional sample embeddings. This strategy refines the prototype representation, thus providing a more accurate prototype for category classification. We performed extensive experiments on popular few-shot learning benchmarks, with the results highlighting the effectiveness of ProtoRefine, especially within the 5-way 1-shot settings. Matching the competitive results of state-of-the-art methods, our work underlines the significant advantage of enhancing prototypes with structurally similar information from the base domain in the context of few-shot learning.

In the past few years, numerous multi-view graph clustering algorithms have been proposed to enhance the clustering performance by exploring information from multiple views. Despite the superior performance, the high time and space expenditures limit their scalability. Accordingly, anchor graph learning has been introduced to alleviate the computational complexity. However, existing approaches can be further improved by the following considerations: (i) Existing anchor-based methods share the same number of anchors across views. This strategy violates the diversity and flexibility of multi-view data distribution. (ii) Searching for the optimal anchor number within hyper-parameters takes much extra tuning time, which makes existing methods impractical. (iii) How to flexibly fuse multi-view anchor graphs of diverse sizes has not been well explored in existing literature. To address the above issues, we propose a novel anchor-based method termed Flexible and Diverse Anchor Graph Fusion for Scalable Multi-view Clustering (FDAGF) in this paper. Instead of manually tuning optimal anchor with massive hyper-parameters, we propose to optimize the contribution weights of a group of pre-defined anchor numbers to avoid extra time expenditure among views. Most importantly, we propose a novel hybrid fusion strategy for multi-size anchor graphs with theoretical proof, which allows flexible and diverse anchor graph fusion. Then, an efficient linear optimization algorithm is proposed to solve the resultant problem. Comprehensive experimental results demonstrate the effectiveness and efficiency of our proposed framework. The source code is available at https://github.com/Jeaninezpp/FDAGF.

Contrastive deep graph clustering, which aims to divide nodes into disjoint groups via contrastive mechanisms, is a challenging research spot. Among the recent works, hard sample mining-based algorithms have achieved great attention for their promising performance. However, we find that the existing hard sample mining methods have two problems as follows. 1) In the hardness measurement, the important structural information is overlooked for similarity calculation, degrading the representativeness of the selected hard negative samples. 2) Previous works merely focus on the hard negative sample pairs while neglecting the hard positive sample pairs. Nevertheless, samples within the same cluster but with low similarity should also be carefully learned. To solve the problems, we propose a novel contrastive deep graph clustering method dubbed Hard Sample Aware Network (HSAN) by introducing a comprehensive similarity measure criterion and a general dynamic sample weighing strategy. Concretely, in our algorithm, the similarities between samples are calculated by considering both the attribute embeddings and the structure embeddings, better revealing sample relationships and assisting hardness measurement. Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones. In this way, our method can mine not only the hard negative samples but also the hard positive sample, thus improving the discriminative capability of the samples further. Extensive experiments and analyses demonstrate the superiority and effectiveness of our proposed method. The source code of HSAN is shared at https://github.com/yueliu1999/HSAN and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.

Multi-view clustering has gained broad attention owing to its capacity to exploit complementary information across multiple data views. Although existing methods demonstrate delightful clustering performance, most of them are of high time complexity and cannot handle large-scale data. Matrix factorization-based models are a representative of solving this problem. However, they assume that the views share a dimension-fixed consensus coefficient matrix and view-specific base matrices, limiting their representability. Moreover, a series of large-scale algorithms that bear one or more hyperparameters are impractical in real-world applications. To address the two issues, we propose an auto-weighted multi-view clustering (AWMVC) algorithm. Specifically, AWMVC first learns coefficient matrices from corresponding base matrices of different dimensions, then fuses them to obtain an optimal consensus matrix. By mapping original features into distinctive low-dimensional spaces, we can attain more comprehensive knowledge, thus obtaining better clustering results. Moreover, we design a six-step alternative optimization algorithm proven to be convergent theoretically. Also, AWMVC shows excellent performance on various benchmark datasets compared with existing ones. The code of AWMVC is publicly available at https://github.com/wanxinhang/AAAI-2023-AWMVC.

Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive and negative sample construction mechanisms limit the performance of existing algorithms from further improvement. 1) The quality of positive samples heavily depends on the carefully designed data augmentations, while inappropriate data augmentations would easily lead to the semantic drift and indiscriminative positive samples. 2) The constructed negative samples are not reliable for ignoring important clustering information. To solve these problems, we propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) by mining the intrinsic supervision information in the high-confidence clustering results. Specifically, instead of conducting complex node or edge perturbation, we construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views. Moreover, to construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples, thus improving the discriminative capability and reliability of the constructed sample pairs. Lastly, we design an objective function to pull close the samples from the same cluster while pushing away those from other clusters by maximizing and minimizing the cross-view cosine similarity between positive and negative samples. Extensive experimental results on six datasets demonstrate the effectiveness of CCGC compared with the existing state-of-the-art algorithms. The code of CCGC is available at https://github.com/xihongyang1999/CCGC on Github.

The success of existing multi-view clustering relies on the assumption of sample integrity across multiple views. However, in real-world scenarios, samples of multi-view are partially available due to data corruption or sensor failure, which leads to incomplete multi-view clustering study (IMVC). Although several attempts have been proposed to address IMVC, they suffer from the following draw-backs: i) Existing methods mainly adopt cross-view contrastive learning forcing the representations of each sample across views to be exactly the same, which might ignore view discrepancy and flexibility in representations; ii) Due to the absence of non-observed samples across multiple views, the obtained prototypes of clusters might be unaligned and biased, leading to incorrect fusion. To address the above issues, we propose a Cross-view Partial Sample and Prototype Alignment Network (CPSPAN) for Deep Incomplete Multi-view Clustering. Firstly, unlike existing contrastive-based methods, we adopt pair-observed data alignment as 'proxy supervised signals' to guide instance-to-instance correspondence construction among views. Then, regarding of the shifted prototypes in IMVC, we further propose a prototype alignment module to achieve incomplete distribution calibration across views. Extensive experimental results showcase the effectiveness of our proposed modules, attaining noteworthy performance improvements when compared to existing IMVC competitors on benchmark datasets.

Multi-view clustering aims to extract valuable information from different sources or perspectives. Over the years, the deep neural network has demonstrated its superior representation learning capability in multi-view clustering and achieved impressive performance. However, most existing deep clustering approaches are dedicated to merging and exploring the consistent latent representation across multiple views while overlooking the abundant complementary information in each view. Furthermore, finding correlations between multiple views in an unsupervised setting is a significant challenge. To tackle these issues, we present a novel Cross-view Topology based Consistent and Complementary information extraction framework, termed CTCC. In detail, deep embedding can be obtained from the bipartite graph learning module for each view individually. CTCC then constructs the cross-view topological graph based on the OT distance between the bipartite graph of each view. Utilizing the above graph, we maximize the mutual information across views to learn consistent information and enhance the complementarity of each view by selectively isolating distributions from each other. Extensive experiments on five challenging datasets verify that CTCC outperforms existing methods significantly.

Multi-view clustering has attracted increasing attention in data mining communities. Despite superior clustering performance, we observe that existing multi-view subspace clustering methods directly fuse multi-view information in the similarity level by merging noisy affinity matrices; and isolate the processes of affinity learning, multiple information fusion and clustering. Both factors may cause insufficient utilization of multi-view information, leading to unsatisfying clustering performance. This paper proposes a novel consensus one-step multi-view subspace clustering (COMVSC) method to address these issues. Instead of directly fusing affinity matrices, COMVSC optimally integrates discriminative partition-level information, which is helpful in eliminating noise among data. Moreover, the affinity matrices, consensus representation and final clustering labels are learned simultaneously in a unified framework. Extensive experiment results on benchmark datasets demonstrate the superiority of our method over other state-of-the-art approaches.

Deep graph clustering, which aims to group the nodes of a graph into disjoint clusters with deep neural networks, has achieved promising progress in recent years. However, the existing methods fail to scale to the large graph with million nodes. To solve this problem, a scalable deep graph clustering method (Dink-Net) is proposed with the idea of dilation and shrink. Firstly, by discriminating nodes, whether being corrupted by augmentations, representations are learned in a self-supervised manner. Meanwhile, the cluster centers are initialized as learnable neural parameters. Subsequently, the clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss in an adversarial manner. By these settings, we unify the two-step clustering, i.e., representation learning and clustering optimization, into an end-to-end framework, guiding the network to learn clustering-friendly features. Besides, Dink-Net scales well to large graphs since the designed loss functions adopt the mini-batch data to optimize the clustering distribution even without performance drops. Both experimental results and theoretical analyses demonstrate the superiority of our method. Compared to the runner-up, Dink-Net achieves $9.62%$ NMI improvement on the ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges. The source code is released: https://github.com/yueliu1999/Dink-Net. Besides, a collection (papers, codes, and datasets) of deep graph clustering is shared on GitHub https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering.

Consistency plays an important role in learning theory. However, in multiple kernel clustering (MKC), the consistency of kernel weights has not been sufficiently investigated. In this work, we fill this gap with a non-asymptotic analysis on the consistency of kernel weights of a novel method termed SimpleMKKM. Under the assumptions of the eigenvalue gap, we give an infinity norm bound as $\widetilde{\mathcal{O}}(k/\sqrt{n})$, where $k$ is the number of clusters and $n$ is the number of samples. On this basis, we establish an upper bound for the excess clustering risk. Moreover, we study the difference of the kernel weights learned from $n$ samples and $r$ points sampled without replacement, and derive its upper bound as $\widetilde{\mathcal{O}}(k\cdot\sqrt{1/r-1/n})$. Based on the above results, we propose a novel strategy with Nyström method to enable SimpleMKKM to handle large-scale datasets with a theoretical learning guarantee. Finally, extensive experiments are conducted to verify the theoretical results and the effectiveness of the proposed large-scale strategy.

Graph anomaly detection (GAD) has attracted increasing attention in machine learning and data mining. Recent works have mainly focused on how to capture richer information to improve the quality of node embeddings for GAD. Despite their significant advances in detection performance, there is still a relative dearth of research on the properties of the task. GAD aims to discern the anomalies that deviate from most nodes. However, the model is prone to learn the pattern of normal samples which make up the majority of samples. Meanwhile, anomalies can be easily detected when their behaviors differ from normality. Therefore, the performance can be further improved by enhancing the ability to learn the normal pattern. To this end, we propose a normality learning-based GAD framework via multi-scale contrastive learning networks (NLGAD for abbreviation). Specifically, we first initialize the model with the contrastive networks on different scales. To provide sufficient and reliable normal nodes for normality learning, we design an effective hybrid strategy for normality selection. Finally, the model is refined with the only input of reliable normal nodes and learns a more accurate estimate of normality so that anomalous nodes can be more easily distinguished. Eventually, extensive experiments on six benchmark graph datasets demonstrate the effectiveness of our normality learning-based scheme on GAD. Notably, the proposed algorithm improves the detection performance (up to 5.89% AUC gain) compared with the state-of-the-art methods. The source code is released at https://github.com/FelixDJC/NLGAD.

Audiovisual data is everywhere in this digital age, which raises higher requirements for the deep learning models developed on them. To well handle the information of the multi-modal data is the key to a better audiovisual modal. We observe that these audiovisual data naturally have temporal attributes, such as the time information for each frame in the video. More concretely, such data is inherently multi-modal according to both audio and visual cues, which proceed in a strict chronological order. It indicates that temporal information is important in multi-modal acoustic event modeling for both intra- and inter-modal. However, existing methods deal with each modal feature independently and simply fuse them together, which neglects the mining of temporal relation and thus leads to sub-optimal performance. With this motivation, we propose a Temporal Multi-modal graph learning method for Acoustic event Classification, called TMac, by modeling such temporal information via graph learning techniques. In particular, we construct a temporal graph for each acoustic event, dividing its audio data and video data into multiple segments. Each segment can be considered as a node, and the temporal relationships between nodes can be considered as timestamps on their edges. In this case, we can smoothly capture the dynamic information in intra-modal and inter-modal. Several experiments are conducted to demonstrate TMac outperforms other SOTA models in performance. Our code is available at https://github.com/MGitHubL/TMac.

Deep graph clustering, which aims to group nodes into disjoint clusters by neural networks in an unsupervised manner, has attracted great attention in recent years. Although the performance has been largely improved, the excellent performance of the existing methods heavily relies on an accurately predefined cluster number, which is not always available in the real-world scenario. To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC). In our proposed method, cluster number determination and unsupervised representation learning are unified into a uniform framework by the reinforcement learning mechanism. Concretely, the discriminative node representations are first learned with the contrastive pretext task. Then, to capture the clustering state accurately with both local and global information in the graph, both node and cluster states are considered. Subsequently, at each state, the qualities of different cluster numbers are evaluated by the quality network, and the greedy action is executed to determine the cluster number. In order to conduct feedback actions, the clustering-oriented reward function is proposed to enhance the cohesion of the same clusters and separate the different clusters. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method. The source code of RGC is shared at https://github.com/yueliu1999/RGC and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.

Anchor-based multi-view graph clustering (AMVGC) has received abundant attention owing to its high efficiency and the capability to capture complementary structural information across multiple views. Intuitively, a high-quality anchor graph plays an essential role in the success of AMVGC. However, the existing AMVGC methods only consider single-structure information, i.e., local or global structure, which provides insufficient information for the learning task. To be specific, the over-scattered global structure leads to learned anchors failing to depict the cluster partition well. In contrast, the local structure with an improper similarity measure results in potentially inaccurate anchor assignment, ultimately leading to sub-optimal clustering performance. To tackle the issue, we propose a novel anchor-based multi-view graph clustering framework termed Efficient Multi-View Graph Clustering with Local and Global Structure Preservation (EMVGC-LG). Specifically, a unified framework with a theoretical guarantee is designed to capture local and global information. Besides, EMVGC-LG jointly optimizes anchor construction and graph learning to enhance the clustering quality. In addition, EMVGC-LG inherits the linear complexity of existing AMVGC methods respecting the sample number, which is time-economical and scales well with the data size. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method.

The success of existing multi-view clustering (MVC) relies on the assumption that all views are complete. However, samples are usually partially available due to data corruption or sensor malfunction, which raises the research of incomplete multi-view clustering (IMVC). Although several anchor-based IMVC methods have been proposed to process the large-scale incomplete data, they still suffer from the following drawbacks: i) Most existing approaches neglect the inter-view discrepancy and enforce cross-view representation to be consistent, which would corrupt the representation capability of the model; ii) Due to the samples disparity between different views, the learned anchor might be misaligned, which we referred as the Anchor-Unaligned Problem for Incomplete data (AUP-ID). Such the AUP-ID would cause inaccurate graph fusion and degrades clustering performance. To tackle these issues, we propose a novel incomplete anchor graph learning framework termed Scalable Incomplete Multi-View Clustering with Structure Alignment (SIMVC-SA). Specially, we construct the view-specific anchor graph to capture the complementary information from different views. In order to solve the AUP-ID, we propose a novel structure alignment module to refine the cross-view anchor correspondence. Meanwhile, the anchor graph construction and alignment are jointly optimized in our unified framework to enhance clustering quality. Through anchor graph construction instead of full graphs, the time and space complexity of the proposed SIMVC-SA is proven to be linearly correlated with the number of samples. Extensive experiments on seven incomplete benchmark datasets demonstrate the effectiveness and efficiency of our proposed method. Our code is publicly available at https://github.com/wy1019/SIMVC-SA.

Benefiting from the strong view-consistent information mining capacity, multi-view contrastive clustering has attracted plenty of attention in recent years. However, we observe the following drawback, which limits the clustering performance from further improvement. The existing multi-view models mainly focus on the consistency of the same samples in different views while ignoring the circumstance of similar but different samples in cross-view scenarios. To solve this problem, we propose a novel Dual contrastive calibration network for Multi-View Clustering (DealMVC). Specifically, we first design a fusion mechanism to obtain a global cross-view feature. Then, a global contrastive calibration loss is proposed by aligning the view feature similarity graph and the high-confidence pseudo-label graph. Moreover, to utilize the diversity of multi-view information, we propose a local contrastive calibration loss to constrain the consistency of pair-wise view features. The feature structure is regularized by reliable class information, thus guaranteeing similar samples have similar features in different views. During the training procedure, the interacted cross-view feature is jointly optimized at both local and global levels. In comparison with other state-of-the-art approaches, the comprehensive experimental results obtained from eight benchmark datasets provide substantial validation of the effectiveness and superiority of our algorithm. We release the code of DealMVC at https://github.com/xihongyang1999/DealMVC on GitHub.

Contrastive graph node clustering via learnable data augmentation is a hot research spot in the field of unsupervised graph learning. The existing methods learn the sampling distribution of a pre-defined augmentation to generate data-driven augmentations automatically. Although promising clustering performance has been achieved, we observe that these strategies still rely on pre-defined augmentations, the semantics of the augmented graph can easily drift. The reliability of the augmented view semantics for contrastive learning can not be guaranteed, thus limiting the model performance. To address these problems, we propose a novel CONtrastiVe Graph ClustEring network with Reliable AugmenTation (COVERT). Specifically, in our method, the data augmentations are processed by the proposed reversible perturb-recover network. It distills reliable semantic information by recovering the perturbed latent embeddings. Moreover, to further guarantee the reliability of semantics, a novel semantic loss is presented to constrain the network via quantifying the perturbation and recovery. Lastly, a label-matching mechanism is designed to guide the model by clustering information through aligning the semantic labels and the selected high-confidence clustering pseudo labels. Extensive experimental results on seven datasets demonstrate the effectiveness of the proposed method. We release the code and appendix of CONVERT at https://github.com/xihongyang1999/CONVERT on GitHub.

With advances in sensing technology, multi-modal data collected from different sources are increasingly available. Multi-modal classification aims to integrate complementary information from multi-modal data to improve model classification performance. However, existing multi-modal classification methods are basically weak in integrating global structural information and providing trustworthy multi-modal fusion, especially in safety-sensitive practical applications (e.g., medical diagnosis). In this paper, we propose a novel Dynamic Poly-attention Network (DPNET) for trustworthy multi-modal classification. Specifically, DPNET has four merits: (i) To capture the intrinsic modality-specific structural information, we design a structure-aware feature aggregation module to learn the corresponding structure-preserved global compact feature representation. (ii) A transparent fusion strategy based on the modality confidence estimation strategy is induced to track information variation within different modalities for dynamical fusion. (iii) To facilitate more effective and efficient multi-modal fusion, we introduce a cross-modal low-rank fusion module to reduce the complexity of tensor-based fusion and activate the implication of different rank-wise features via a rank attention mechanism. (iv) A label confidence estimation module is devised to drive the network to generate more credible confidence. An intra-class attention loss is introduced to supervise the network training. Extensive experiments on four real-world multi-modal biomedical datasets demonstrate that the proposed method achieves competitive performance compared to other state-of-the-art ones.

Kullback-Leibler (KL) divergence is one of the most important measures to calculate the difference between probability distributions. In this paper, we theoretically study several properties of KL divergence between multivariate Gaussian distributions. Firstly, for any two $n$-dimensional Gaussian distributions $\mathcal{N}_1$ and $\mathcal{N}_2$, we prove that when $KL(\mathcal{N}_2||\mathcal{N}_1)\leq \varepsilon\ (\varepsilon>0)$ the supremum of $KL(\mathcal{N}_1||\mathcal{N}_2)$ is $(1/2)\left((-W_{0}(-e^{-(1+2\varepsilon)}))^{-1}+\log(-W_{0}(-e^{-(1+2\varepsilon)})) -1 \right)$, where $W_0$ is the principal branch of Lambert $W$ function. For small $\varepsilon$, the supremum is $\varepsilon + 2\varepsilon^{1.5} + O(\varepsilon^2)$. This quantifies the approximate symmetry of small KL divergence between Gaussian distributions. We further derive the infimum of $KL(\mathcal{N}_1||\mathcal{N}_2)$ when $KL(\mathcal{N}_2||\mathcal{N}_1)\geq M\ (M>0)$. We give the conditions when the supremum and infimum can be attained. Secondly, for any three $n$-dimensional Gaussian distributions $\mathcal{N}_1$, $\mathcal{N}_2$, and $\mathcal{N}_3$, we theoretically show that an upper bound of $KL(\mathcal{N}_1||\mathcal{N}_3)$ is $3\varepsilon_1+3\varepsilon_2+2\sqrt{\varepsilon_1\varepsilon_2}+o(\varepsilon_1)+o(\varepsilon_2)$ when $KL(\mathcal{N}_1||\mathcal{N}_2)\leq \varepsilon_1$ and $KL(\mathcal{N}_2||\mathcal{N}_3)\leq \varepsilon_2$ ($\varepsilon_1,\varepsilon_2\ge 0$). This reveals that KL divergence between Gaussian distributions follows a relaxed triangle inequality. Note that, all these bounds in the theorems presented in this work are independent of the dimension $n$. Finally, we discuss several applications of our theories in deep learning, reinforcement learning, and sample complexity research.

Reasoning on temporal knowledge graphs (TKGR), aiming to infer missing events along the timeline, has been widely studied to alleviate incompleteness issues in TKG, which is composed of a series of KG snapshots at different timestamps. Two types of information, i.e., intra-snapshot structural information and inter-snapshot temporal interactions, mainly contribute to the learned representations for reasoning in previous models. However, these models fail to leverage (1) semantic correlations between relationships for the former information and (2) the periodic temporal patterns along the timeline for the latter one. Thus, such insufficient mining manners hinder expressive ability, leading to sub-optimal performances. To address these limitations, we propose a novel reasoning model, termed RPC, which sufficiently mines the information underlying the Relational correlations and Periodic patterns via two novel Correspondence units, i.e., relational correspondence unit (RCU) and periodic correspondence unit (PCU). Concretely, relational graph convolutional network (RGCN) and RCU are used to encode the intra-snapshot graph structural information for entities and relations, respectively. Besides, the gated recurrent units (GRU) and PCU are designed for sequential and periodic inter-snapshot temporal interactions, separately. Moreover, the model-agnostic time vectors are generated by time2vector encoders to guide the time-dependent decoder for fact scoring. Extensive experiments on six benchmark datasets show that RPC outperforms the state-of-the-art TKGR models, and also demonstrate the effectiveness of two novel strategies in our model.

Clustering methods have been widely used in single-cell RNA-seq data for investigating tumor heterogeneity. Since traditional clustering methods fail to capture the high-dimension methods, deep clustering methods have drawn increasing attention these years due to their promising strengths on the task. However, existing methods consider either the attribute information of each cell or the structure information between different cells. In other words, they cannot sufficiently make use of all of this information simultaneously. To this end, we propose a novel single-cell deep fusion clustering model, which contains two modules, i.e. an attributed feature clustering module and a structure-attention feature clustering module. More concretely, two elegantly designed autoencoders are built to handle both features regardless of their data types. Experiments have demonstrated the validity of the proposed approach, showing that it is efficient to fuse attributes, structure, and attention information on single-cell RNA-seq data. This work will be further beneficial for investigating cell subpopulations and tumor microenvironment. The Python implementation of our work is now freely available at https://github.com/DayuHuu/scDFC.

Many real-world problems deal with collections of data with missing values, e.g., RNA sequential analytics, image completion, video processing, etc. Usually, such missing data is a serious impediment to a good learning achievement. Existing methods tend to use a universal model for all incomplete data, resulting in a suboptimal model for each missingness pattern. In this paper, we present a general model for learning with incomplete data. The proposed model can be appropriately adjusted with different missingness patterns, alleviating competitions between data. Our model is based on observable features only, so it does not incur errors from data imputation. We further introduce a low-rank constraint to promote the generalization ability of our model. Analysis of the generalization error justifies our idea theoretically. In additional, a subgradient method is proposed to optimize our model with a proven convergence rate. Experiments on different types of data show that our method compares favorably with typical imputation strategies and other state-of-the-art models for incomplete data. More importantly, our method can be seamlessly incorporated into the neural networks with the best results achieved. The source code is released at https://github.com/YS-GONG/missingness-patterns.

We propose a simple yet effective multiple kernel clustering algorithm, termed simple multiple kernel k-means (SimpleMKKM). It extends the widely used supervised kernel alignment criterion to multi-kernel clustering. Our criterion is given by an intractable minimization-maximization problem in the kernel coefficient and clustering partition matrix. To optimize it, we equivalently rewrite the minimization-maximization formulation as a minimization of an optimal value function, prove its differenentiablity, and design a reduced gradient descent algorithm to decrease it. Furthermore, we prove that the resultant solution of SimpleMKKM is the global optimum. We theoretically analyze the performance of SimpleMKKM in terms of its clustering generalization error. After that, we develop extensive experiments to investigate the proposed SimpleMKKM from the perspectives of clustering accuracy, advantage on the formulation and optimization, variation of the learned consensus clustering matrix with iterations, clustering performance with varied number of samples and base kernels, analysis of the learned kernel weight, the running time and the global convergence. The experimental study demonstrates the effectiveness of the proposed SimpleMKKM by considerably and consistently outperforming state of the art multiple kernel clustering alternatives. In addition, the ablation study shows that the improved clustering performance is contributed by both the novel formulation and new optimization. Our work provides a more effective approach to integrate multi-view data for clustering, and this could trigger novel research on multiple kernel clustering. The source code and data for SimpleMKKM are available at https://github.com/xinwangliu/SimpleMKKMcodes/.

The newly proposed localized simple multiple kernel k-means (SimpleMKKM) provides an elegant clustering framework which sufficiently considers the potential variation among samples. Although achieving superior clustering performance in some applications, we observe that it is required to pre-specify an extra hyperparameter, which determines the size of the localization. This greatly limits its availability in practical applications since there is a little guideline to set a suitable hyperparameter in clustering tasks. To overcome this issue, we firstly parameterize a neighborhood mask matrix as a quadratic combination of a set of pre-computed base neighborhood mask matrices, which corresponds to a group of hyperparameters. We then propose to jointly learn the optimal coefficient of these neighborhood mask matrices together with the clustering tasks. By this way, we obtain the proposed hyperparameter-free localized SimpleMKKM, which corresponds to a more intractable minimization-minimization-maximization optimization problem. We rewrite the resultant optimization as a minimization of an optimal value function, prove its differentiability, and develop a gradient based algorithm to solve it. Furthermore, we theoretically prove that the obtained optimum is the global one. Comprehensive experimental study on several benchmark datasets verifies its effectiveness, comparing with several state-of-the-art counterparts in the recent literature. The source code for hyperparameter-free localized SimpleMKKM is available at https://github.com/xinwangliu/SimpleMKKMcodes/.

Kernel method is a proven technique in multi-view learning. It implicitly defines a Hilbert space where samples can be linearly separated. Most kernel-based multi-view learning algorithms compute a kernel function aggregating and compressing the views into a single kernel. However, existing approaches compute the kernels independently for each view. This ignores complementary information across views and thus may result in a bad kernel choice. In contrast, we propose the Contrastive Multi-view Kernel - a novel kernel function based on the emerging contrastive learning framework. The Contrastive Multi-view Kernel implicitly embeds the views into a joint semantic space where all of them resemble each other while promoting to learn diverse views. We validate the method's effectiveness in a large empirical study. It is worth noting that the proposed kernel functions share the types and parameters with traditional ones, making them fully compatible with existing kernel theory and application. On this basis, we also propose a contrastive multi-view clustering framework and instantiate it with multiple kernel k-means, achieving a promising performance. To the best of our knowledge, this is the first attempt to explore kernel generation in multi-view setting and the first approach to use contrastive learning for a multi-view kernel learning.

Existing unsupervised outlier detection (OD) solutions face a grave challenge with surging visual data like images. Although deep neural networks (DNNs) prove successful for visual data, deep OD remains difficult due to OD’s unsupervised nature. This paper proposes a novel framework namedE$^{3}$Outlierthat can performeffective andend-to-end deep outlier removal. Its core idea is to introduceself-supervisioninto deep OD. Specifically, our major solution is to adopt a discriminative learning paradigm that creates multiple pseudo classes from given unlabeled data by various data operations, which enables us to apply prevalent discriminative DNNs (e.g. ResNet) to the unsupervised OD problem. Then, with theoretical and empirical demonstration, we argue that inlier priority, a property that encourages DNN to prioritize inliers during self-supervised learning, makes it possible to perform end-to-end OD. Meanwhile, unlike frequently-used outlierness measures (e.g. density, proximity) in previous OD methods, we explore network uncertainty and validate it as a highly effective outlierness measure, while two practical score refinement strategies are also designed to improve OD performance. Finally, in addition to the discriminative learning paradigm above, we also explore the solutions that exploit other learning paradigms (i.e. generative learning and contrastive learning) to introduce self-supervision forE$^{3}$Outlier. Such extendibility not only brings further performance gain on relatively difficult datasets, but also enablesE$^{3}$Outlierto be applied to other OD applications like video abnormal event detection. Extensive experiments demonstrate thatE$^{3}$Outliercan considerably outperform state-of-the-art counterparts by 10%-30% AUROC. Demo codes are available athttps://github.com/demonzyj56/E3Outlier.

Hyperspectral band selection aims to identify an optimal subset of bands for hyperspectral images (HSIs). For most existing clustering-based band selection methods, they directly stretch each band into a single feature vector and employ the pixelwise features to address band redundancy. In this way, they do not take full consideration of the spatial information and deal with the importance of different regions in HSIs, which leads to a nonoptimal selection. To address these issues, a region-aware hierarchical latent feature representation learning-guided clustering (HLFC) method is proposed. Specifically, in order to fully preserve the spatial information of HSIs, the superpixel segmentation algorithm is adopted to segment HSIs into multiple regions first. For each segmented region, the similarity graph is constructed to reflect the bands-wise similarity, and its corresponding Laplacian matrix is generated for learning low-dimensional latent features in a hierarchical way. All latent features are then fused to form a unified feature representation of HSIs. Finally, k -means clustering is utilized on the unified feature representation matrix to generate multiple clusters from which the band with maximum information entropy is selected to form the final subset of bands. Extensive experimental results demonstrate that the proposed clustering method can achieve superior performance than the state-of-the-art representative methods on the band selection. The demo code of this work is publicly available at https://github.com/WangJun2023/HLFC.

Localized incomplete multiple kernel k -means (LI-MKKM) is recently put forward to boost the clustering accuracy via optimally utilizing a quantity of prespecified incomplete base kernel matrices. Despite achieving significant achievement in a variety of applications, we find out that LI-MKKM does not sufficiently consider the diversity and the complementary of the base kernels. This could make the imputation of incomplete kernels less effective, and vice versa degrades on the subsequent clustering. To tackle these problems, an improved LI-MKKM, called LI-MKKM with matrix-induced regularization (LI-MKKM-MR), is proposed by incorporating a matrix-induced regularization term to handle the correlation among base kernels. The incorporated regularization term is beneficial to decrease the probability of simultaneously selecting two similar kernels and increase the probability of selecting two kernels with moderate differences. After that, we establish a three-step iterative algorithm to solve the corresponding optimization objective and analyze its convergence. Moreover, we theoretically show that the local kernel alignment is a special case of its global one with normalizing each base kernel matrices. Based on the above observation, the generalization error bound of the proposed algorithm is derived to theoretically justify its effectiveness. Finally, extensive experiments on several public datasets have been conducted to evaluate the clustering performance of the LI-MKKM-MR. As indicated, the experimental results have demonstrated that our algorithm consistently outperforms the state-of-the-art ones, verifying the superior performance of the proposed algorithm.

Deep learning-based hyperspectral image (HSI) classification and object detection techniques have gained significant attention due to their vital role in image content analysis, interpretation, and broader HSI applications. However, current hyperspectral object detection approaches predominantly emphasize spectral or spatial information, overlooking the valuable complementary relationship between these two aspects. In this study, we present a novel Spectral-Spatial Aggregation (S2ADet) object detector that effectively harnesses the rich spectral and spatial complementary information inherent in the hyperspectral image. S2ADet comprises a hyperspectral information decoupling (HID) module, a two-stream feature extraction network, and a one-stage detection head. The HID module processes hyperspectral data by aggregating spectral and spatial information via band selection and principal components analysis, consequently reducing redundancy. Based on the acquired spectral and spatial aggregation information, we propose a feature aggregation two-stream network for interacting spectral-spatial features. Furthermore, to address the limitations of existing databases, we annotate an extensive dataset, designated as HOD3K, containing 3,242 hyperspectral images captured across diverse real-world scenes and encompassing three object classes. These images possess a resolution of 512×256 pixels and cover 16 bands ranging from 470 nm to 620 nm. Comprehensive experiments on two datasets demonstrate that S2ADet surpasses existing state-of-the-art methods, achieving robust and reliable results. The demo code and dataset of this work are publicly available at https://github.com/hexiao-cs/S2ADet.

Remote sensing change detection (RSCD) aims to explore surface changes from co-registered pair of images. However, the high cost of memory and computation in previous convolutional neural network (CNN)-based methods prevent their successes from being applied to real-world applications. Therefore, we propose a novel lightweight network, which identifies changes based on the features extracted by mobile networks via progressive feature aggregation and supervised attention, termed as A2Net. Considering the less powerful representation capability of mobile networks, we design a neighbor aggregation module (NAM) to fuse features within nearby stages of the backbone to strengthen the representation capability of temporal features. Then, we propose a progressive change identifying module (PCIM) to extract temporal difference information from bitemporal features. Besides, we design a supervised attention module (SAM) to reweight features for effectively aggregating multilevel features from high levels to low levels. With NAM, PCIM, and SAM incorporated, A2Net can achieve favorable results compared with the state-of-the-art methods on three challenging RSCD datasets with fewer parameters (3.78 M) and lower computation costs (6.02 G). The demo code of this work is publicly available athttps://github.com/guanyuezhen/A2Net.

As an effective manner to reduce data redundancy and processing inconvenience, hyperspectral band selection aims to select a subset of informative and discriminative bands from the original data cube. Although a large number of approaches have been proposed and obtained great success, they still face at least two issues. Firstly, most of the previous methods only consider the redundancy between neighbor bands, while the global information has been ignored. Secondly, each band is often treated as a whole and reshaped to a feature vector without considering the spatial structure of different regions. In this paper, in order to address these issues, we propose a spatial and spectral structure preserved self-representation model for unsupervised hyperspectral band selection without using any label information, referred to as S4P briefly. Different from previous methods that stretch each band into a feature vector, the first principal component of the original hyperspectral cube is segmented into different superpixels, which can reflect the spatial structure of homogeneous regions. Then each band can be represented by a superpixel level feature vector and the self-representation model is utilized to learn the spectral correlation of different bands. In addition, an adaptive and weighted multiple graph fusion term is designed to generate a unified similarity graph between different superpixels, which is used to capture the spatial structure in the self-representation space. Finally, anl2,1-norm is imposed on the self-representation coefficient matrix to measure the band importance. We design an alternative update scheme to optimize the resultant problem, the self-representation coefficient matrix and the superpixel-wise similarity graph can boost each other during the updating process to obtain optimal results. Extensive experiments with detailed analysis of three public datasets are conducted to validate the superiority of the proposed S4P when compared with other state-of-the-art competitors.

Although great progress has been sparked in video anomaly detection (VAD) by deep neural networks (DNNs), existing solutions still fall short in two aspects: (1) The extraction of video events cannot be both precise and comprehensive. (2) The semantics and temporal context are under-explored. To tackle above issues, we are inspired by cloze tests in language education and propose a novel approach namedVisual Cloze Completion(VCC), which conducts VAD by completingvisual cloze tests(VCTs). Specifically, VCC first localizes each video event and encloses it into a spatio-temporal cube (STC). To realize both precise and comprehensive event extraction, appearance and motion are used as complementary cues to mark the object region associated with each event. For each marked region, a normalized patch sequence is extracted from several neighboring frames and stacked into a STC. With each patch and the patch sequence of a STC regarded as a visual “word” and “sentence” respectively, we deliberately erase a certain “word” (patch) to yield a VCT. Then, the VCT is completed by training DNNs to infer the erased patch and its optical flow via video semantics. Meanwhile, VCC fully exploits temporal context by alternatively erasing each patch in temporal context and creating multiple VCTs. Furthermore, we propose localization-level, event-level, model-level and decision-level solutions to enhance VCC, which can further exploit VCC’s potential and produce significant VAD performance improvement. Extensive experiments demonstrate that VCC achieves highly competitive VAD performance.

Recently, metric-based meta-learning methods have been effectively applied to few-shot image classification. These methods classify images based on the relationship between samples in an embedding space, avoiding over-fitting that can occur when training classifiers with limited samples. However, finding an embedding space with good generalization properties remains a challenge. Our work highlights that having an initial manifold space that preserves sample neighbor relationships can prevent the metric model from reaching a suboptimal solution. We propose a feature learning method that leverages Instance Neighbor Constraints (INC). This theory is thoroughly evaluated and analyzed through experiments, demonstrating its effectiveness in improving the efficiency of learning and the overall performance of the model. We further integrate the INC into an alternate optimization training framework (AOT) that leverages both batch learning and episode learning to better optimize the metric-based model. We conduct extensive experiments on 5-way 1-shot and 5-way 5-shot settings on four popular few-shot image benchmarks: miniImageNet, tieredImageNet, Fewshot-CIFAR100 (FC100), and Caltech-UCSD Birds-200-2011(CUB). Results show that our method achieves consistent performance gains on benchmarks and state-of-the-art performance. Our findings suggest that initializing the embedding space appropriately and leveraging both batch and episode learning can significantly improve few-shot learning performance.

Consensus clustering provides an elegant framework to aggregate multiple weak clustering results to learn a consensus one that is more robust and stable than a single result. However, most of the existing methods usually use all data for consensus learning, whereas ignoring the side effects caused by some unreliable or difficult data. To address this issue, in this article, we propose a novel self-paced consensus clustering method with adaptive bipartite graph learning to gradually involve data from more reliable to less reliable ones in consensus learning. At first, we construct an initial bipartite graph from the base results, where the nodes represent the clusters and instances, and the edges indicate that an instance belongs to a cluster. Then, we adaptively learn a structured bipartite graph from this initial one by self-paced learning, i.e., we automatically determine the reliability of each edge with adaptive cluster similarity measuring and involve the edges in bipartite graph learning in order of their reliability. At last, we obtain the final consensus result from the learned structured bipartite graph. We conduct extensive experiments on both toy and benchmark datasets, and the results show the effectiveness and superiority of our method. The codes of this article are released in http://Doctor-Nobody.github.io/codes/code_SCCABG.zip.

Multi-view clustering aims at integrating information from different views to improve clustering performance. Recent methods integrate multiple view-specific partition matrices to seek a consensus one and have demonstrated promising clustering performance in various applications. However, the clustering performance of such methods heavily relies on the consensus partition matrix estimated by the arithmetic mean in euclidean space and thus is highly susceptible to noise corruption. To this end, this article proposes to learn a consensus partition matrix through the geometric mean on the manifold to achieve robust clustering. Specifically, the multiple view-specific partition matrices can be regarded as points residing in the Stiefel manifold and enable a manifold-based integration. Consequently, the view-specific partition matrices are integrated by estimating a consensus partition matrix as the center point on the Stiefel manifold. Such a partition integration boils down to the Fréchet mean problem on a manifold, which is solved by the intrinsic manifold-based optimization and proves effective in providing a more robust estimation against noise. Experimental results on seven benchmark datasets demonstrate the effectiveness and noise-robustness of our proposed method in comparison to eight competitive methods.

Multi-view learning becomes increasingly attractive and promising because multimodal or multi-view data are commonly encountered in real-world applications. In this study, we develop a novel multi-view Takagi–Sugeno–Kang (TSK) fuzzy system framework to handle classification problems for such data. We propose an anchor and graph subspace clustering strategy to discover and represent the actual latent data distribution for each view separately. In this way, the discriminate anchors (landmarks) are learned to capture the main structure of the multi-view data. This strategy also provides a computationally efficient clustering algorithm with respect to the number of instances. These resulting anchors are formed as the prototypes of information granules (IGs) for fuzzy modeling. Then we construct an information-granule-based multi-view TSK fuzzy classification model inherited from the natural interpretability of fuzzy rule-based systems. Concretely, the relationship between the multi-view input and label output spaces is depicted by IGs-oriented fuzzy rules. The experimental studies involve various commonly used benchmark datasets, which indicate that our proposed method achieves comparable or better performance compared to the state-of-the-art algorithms.

Unsupervised bipartite graph learning has been a hotpot in multi-view clustering, to tackle the restricted scalability issue of traditional full graph clustering in large-scale applications. However, the existing bipartite graph clustering paradigm pays little attention to the adverse impact of noisy features on learning process. To further facilitate this part of research, apart from simply reweighting features to depress the noisy ones, we take the first step towards analyzing the induced adverse impact via theoretical and experimental investigations. One crucial finding in this paper is that the existence of noisy features will incur “anchor shift” phenomenon, which deviates the potential representations of anchors and then degrades performance. To this end, we propose a coupled noisy feature filter mechanism with automatically finding feature importance to remedy the anchor shift issue in this paper. Apart from leveraging features, we theoretically analyze the bounds of proposed feature-adaptive bipartite graph's fuzzy membership. Specifically, distinguishing features' discrimination will increase the fuzzy membership to achieve soft partitions against the potential inaccurate absolute relationship. With the afore-mentioned merits, our proposed multi-view bipartite graph clustering with coupled noisy feature filter model (MVBGC-NFF) provides novel and interesting insights on the feature level of anchor shift. The effectiveness and efficiency of MVBGC-NFF are demonstrated on synthetic and real-world datasets with improving clustering performance, increasing fuzzy membership, and filtering noisy features. The code is available onhttps://github.com/liliangnudt/MVBGC-NFF.

Online Event-based social networks (EBSNs), such as Meetup and Whova, which provide platforms for users to publish, arrange and participate in events, have become increasingly popular. A major challenge for managing EBSNs is to generate the most satisfactory event arrangement, i.e. events are scheduled at the reasonable time to attract maximum number of participants. Existing approaches usually focus on assigning a set of events organized by the same group to time intervals, but ignore the competitive relationships among different event organizers, which will lead to event time allocations unacceptable to organizers. Thus, a more intelligent EBSNs platform that allocates social events properly in a global view (i.e. the perspective of platform) is desired. In this paper, we first formally define the problem of Platform-oriented Event Time Allocation (PETA), which contains two parts: the prediction of event feasible time period and the event time allocation. Unfortunately, we find that the PETA problem is NP-hard due to the global conflict constraints on events. Thus, we propose design a greedy algorithm and two approximation algorithms to solve the PETA problem. Finally, we conduct extensive experiments on both real and synthetic datasets to test the effectiveness and efficiency of the proposed algorithms.

Multi-view spectral clustering, which exploits the complementary information among graphs of diverse views to obtain superior clustering results, has attracted intensive attention recently. However, most existing multi-view spectral clustering methods obtain the clustering partitions in a two-step scheme, i.e., spectral embedding and subsequent$k$-means. This two-step scheme inevitably seeks sub-optimal clustering results due to the information loss during the two-steps processes. Besides, existing multi-view spectral clustering methods do not jointly utilize the information of graphs and embedding matrices, which also degrades final clustering results. To solve these issues, we propose a unified one-step multi-view spectral clustering method, which integrates the spectral embedding and$k$-means into a unified framework to obtain discrete clustering labels with a one-step strategy. Under the observation that the inner product of the embedding matrix is a low-rank approximation of the graph, we combine graphs and embedding matrices of different views to obtain a unified graph. Then, we directly capture the discrete clustering indicator matrix from the unified graph. Furthermore, we design an effective optimization algorithm to solve the resultant problem. Finally, a set of experiments on various datasets are conducted to verify the effectiveness of the proposed method. The demo code of this work is publicly available atrgb]0,0,1https://github.com/guanyuezhen/UOMvSC.

This paper proposes a simple interpolation Oversampling method with the purpose of Reliably Expanding the Minority class regions (OREM). OREM first finds the candidate minority region around each original minority sample, then exploits this region to further identify those clean subregions without distributing any majority sample. The synthetic samples are only allowed to generate in the clean subregions, so that the regions of the minority class can be broadened reliably. Given that the learning from multiclass imbalanced data is more challenging as compared to two-class scenarios, we also extend OREM to handle multiclass imbalance problems by leveraging an iteration procedure of generating synthetic samples, consequently leading to a multiclass oversampling algorithm OREM-M. The key peculiarity of OREM-M is to reduce the class overlapping not only between the synthetic minority and original samples, but also from the synthetic samples of different minority classes. In this way, OREM-M ensures that the data of each class after oversampling can be modeled well. In addition, we embed OREM into boosting framework to develop a new ensemble method OREMBoost addressing class imbalance problems. Extensive experiments demonstrate the effectiveness of the proposed OREM, OREM-M, and OREMBoost.

Multi-view clustering, which appropriately integrates information from multiple sources to reveal data’s inherent structure, is gaining traction in clustering. Though existing procedures have yielded satisfactory results, we observe that they have neglected the inherent local structure in the base kernels. This may cause adverse effects on clustering. To solve the problem, we introduce LF-MKC-LKA, a simple yet effective late fusion multiple kernel clustering with local kernel alignment maximisation approach. In particular, we first determine the nearest$k$neighbours in the average kernel space for each sample and record the information in the nearest neighbor indicator matrix. Then, the nearest neighbor indicator matrix can be used to generate local structure matrix of each sample. The local kernels of each view may then be generated using the local structure matrix, retaining just the highly confident local similarities for learning the intrinsic global manifold of data. They can also be utilised to keep the block diagonal structure and improve the robustness of the underlying kernels against noise.We input the local kernels of each view into the kernel$k$-means (KKM) algorithm and get the local base partitions. Finally, we use a three-step iterative optimization approach to maximize the alignment of the consensus partition using base partitions and a regularisation term. As demonstrated, a significant number of trials on 11 multi-kernel benchmark datasets have shown that the proposed LF-MKC-LKA is effective and efficient. A number of experiments are also designed to demonstrate the fast convergence, excellent performance, robustness and low parameter sensitivity of the algorithm. Our code can be find athttps://github.com/TiejianZhang/TMM21-LF-MKC-LKA.

In order to solve the time-varying quadratic programming (TVQP) problem more effectively, a new self-adaptive zeroing neural network (ZNN) is designed and analyzed in this article by using the Takagi-Sugeno fuzzy logic system (TSFLS) and thus called the Takagi-Sugeno (T-S) fuzzy ZNN (TSFZNN). Specifically, a multiple-input-single-output TSFLS is designed to generate a self-adaptive convergence factor to construct the TSFZNN model. In order to obtain finite- or predefined-time convergence, four novel activation functions (AFs) [namely, power-bi-sign AF (PBSAF), tanh-bi-sign AF (TBSAF), exp-bi-sign AF (EBSAF), and sinh-bi-sign AF (SBSAF)] are developed and applied in the TSFZNN model for solving the TVQP problem. Both theoretical proofs and experimental simulations show that the TSFZNN model using PBSAF or TBSAF has the property of converging in a finite time, and the TSFZNN model using EBSAF or SBSAF has the property of converging in a predefined time, which have superior convergence performance compared to the traditional ZNN model.

Multiple kernel clustering (MKC) optimally utilizes a group of pre-specified base kernels to improve clustering performance. Among existing MKC algorithms, the recently proposed late fusion MKC methods demonstrate promising clustering performance in various applications and enjoy considerable computational acceleration. However, we observe that the kernel partition learning and late fusion processes are separated from each other in the existing mechanism, which may lead to suboptimal solutions and adversely affect the clustering performance. In this article, we propose a novel late fusion multiple kernel clustering with proxy graph refinement (LFMKC-PGR) framework to address these issues. First, we theoretically revisit the connection between late fusion kernel base partition and traditional spectral embedding. Based on this observation, we construct a proxy self-expressive graph from kernel base partitions. The proxy graph in return refines the individual kernel partitions and also captures partition relations in graph structure rather than simple linear transformation. We also provide theoretical connections and considerations between the proposed framework and the multiple kernel subspace clustering. An alternate algorithm with proved convergence is then developed to solve the resultant optimization problem. After that, extensive experiments are conducted on 12 multi-kernel benchmark datasets, and the results demonstrate the effectiveness of our proposed algorithm. The code of the proposed algorithm is publicly available at https://github.com/wangsiwei2010/graphlatefusion_MKC.

Multiple kernel clustering (MKC) has recently achieved remarkable progress in fusing multisource information to boost the clustering performance. However, the$\mathcal {O}({n}^{2})$memory consumption and$\mathcal {O}({n}^{3})$computational complexity prohibit these methods from being applied into median- or large-scale applications, where$n$denotes the number of samples. To address these issues, we carefully redesign the formulation of subspace segmentation-based MKC, which reduces the memory and computational complexity to$\mathcal {O}({n})$and$\mathcal {O}({n}^{2})$, respectively. The proposed algorithm adopts a novel sampling strategy to enhance the performance and accelerate the speed of MKC. Specifically, we first mathematically model the sampling process and then learn it simultaneously during the procedure of information fusion. By this way, the generated anchor point set can better serve data reconstruction across different views, leading to improved discriminative capability of the reconstruction matrix and boosted clustering performance. Although the integrated sampling process makes the proposed algorithm less efficient than the linear complexity algorithms, the elaborate formulation makes our algorithm straightforward for parallelization. Through the acceleration of GPU and multicore techniques, our algorithm achieves superior performance against the compared state-of-the-art methods on six datasets with comparable time cost to the linear complexity algorithms.

Graph-based multi-view clustering (G-MVC) constructs a graphical representation of each view and then fuses them to a unified graph for clustering. Though demonstrating promising clustering performance in various applications, we observe that their formulations are usually non-convex, leading to a local optimum. In this paper, we propose a novel MVC algorithm termed robust graph-based multi-view clustering (RG-MVC) to address this issue. In particular, we define a min-max formulation for robust learning and then rewrite it as a convex and differentiable objective function whose convexity and differentiability are carefully proved. Thus, we can efficiently solve the resultant problem using a reduced gradient descent algorithm, and the corresponding solution is guaranteed to be globally optimal. As a consequence, although our algorithm is free of hyper-parameters, it has shown good robustness against noisy views. Extensive experiments on benchmark datasets verify the superiority of the proposed method against the compared state-of-the-art algorithms. Our codes and appendix are available at https://github.com/wx-liang/RG-MVC.

Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different groups, has attracted intensive attention in recent years. However, we observe that, in the process of node encoding, existing methods suffer from representation collapse which tends to map all data into the same representation. Consequently, the discriminative capability of the node representation is limited, leading to unsatisfied clustering performance. To address this issue, we propose a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner. Specifically, in our method, we first design a siamese network to encode samples. Then by forcing the cross-view sample correlation matrix and cross-view feature correlation matrix to approximate two identity matrices, respectively, we reduce the information correlation in the dual-level, thus improving the discriminative capability of the resulting features. Moreover, in order to alleviate representation collapse caused by over-smoothing in GCN, we introduce a propagation regularization term to enable the network to gain long-distance information with the shallow network structure. Extensive experimental results on six benchmark datasets demonstrate the effectiveness of the proposed DCRN against the existing state-of-the-art methods. The code of DCRN is available at https://github.com/yueliu1999/DCRN and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.

Multi-view subspace clustering (MVSC) optimally integrates multiple graph structure information to improve clustering performance. Recently, many anchor-based variants are proposed to reduce the computational complexity of MVSC. Though achieving considerable acceleration, we observe that most of them adopt fixed anchor points separating from the subsequential anchor graph construction, which may adversely affect the clustering performance. In addition, post-processing is required to generate discrete clustering labels with additional time consumption. To address these issues, we propose a scalable and parameter-free MVSC method to directly output the clustering labels with optimal anchor graph, termed as Efficient One-pass Multi-view Subspace Clustering with Consensus Anchors (EOMSC-CA). Specially, we combine anchor learning and graph construction into a uniform framework to boost clustering performance. Meanwhile, by imposing a graph connectivity constraint, our algorithm directly outputs the clustering labels without any post-processing procedures as previous methods do. Our proposed EOMSC-CA is proven to be linear complexity respecting to the data size. The superiority of our EOMSC-CA over the effectiveness and efficiency is demonstrated by extensive experiments. Our code is publicly available at https://github.com/Tracesource/EOMSC-CA.

Multiple kernel clustering aims to seek an appropriate combination of base kernels to mine inherent non-linear information for optimal clustering. Late fusion algorithms generate base partitions independently and integrate them in the following clustering procedure, improving the overall efficiency. However, the separate base partition generation leads to inadequate negotiation with the clustering procedure and a great loss of beneficial information in corresponding kernel matrices, which negatively affects the clustering performance. To address this issue, we propose a novel algorithm, termed as Fusion Multiple Kernel k-means (FMKKM), which unifies base partition learning and late fusion clustering into one single objective function, and adopts early fusion technique to capture more sufficient information in kernel matrices. Specifically, the early fusion helps base partitions keep more beneficial kernel details, and the base partitions learning further guides the generation of consensus partition in the late fusion stage, while the late fusion provides positive feedback on two former procedures. The close collaboration of three procedures results in a promising performance improvement. Subsequently, an alternate optimization method with promising convergence is developed to solve the resultant optimization problem. Comprehensive experimental results demonstrate that our proposed algorithm achieves state-of-the-art performance on multiple public datasets, validating its effectiveness. The code of this work is publicly available at https://github.com/ethan-yizhang/Fusion-Multiple-Kernel-K-means.

We introduce Displacement Aware Relation Module (DisARM), a novel neural network module for enhancing the performance of 3D object detection in point cloud scenes. The core idea is extracting the most principal contextual information is critical for detection while the target is incomplete or featureless. We find that relations between proposals provide a good representation to describe the context. However, adopting relations between all the object or patch proposals for detection is inefficient, and an imbalanced combination of local and global relations brings extra noise that could mislead the training. Rather than working with all relations, we find that training with relations only between the most representative ones, or an-chors, can significantly boost the detection performance. Good anchors should be semantic-aware with no ambiguity and able to describe the whole layout of a scene with no redundancy. To find the anchors, we first perform a preliminary relation anchor module with an objectness-aware sampling approach and then devise a displacement based module for weighing the relation importance for better utilization of contextual information. This lightweight relation module leads to significantly higher accuracy of object instance detection when being plugged into the state-of-the-art detectors. Evaluations on the public benchmarks of real-world scenes show that our method achieves the state-of-the-art performance on both SUN RGB-D and Scan-Net V2. The code and models are publicly available at https://github.com/YaraDuan/DisARM.

Multiview clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations. Most previous methods hold the assumption that each instance appears in all views. However, it is not uncommon to see that some views may contain some missing instances, which gives rise to incomplete multi-view clustering (IMVC) in literature. Although many IMVC methods have been recently proposed, they always encounter high complexity and expensive time expenditure from being applied into large-scale tasks. In this paper, we present a flexible highly-efficient incomplete large-scale multi-view clustering approach based on bipartite graph framework to solve these issues. Specifically, we formalize multi-view anchor learning and incomplete bipartite graph into a unified framework, which coordinates with each other to boost cluster performance. By introducing the flexible bipartite graph framework to handle IMVC for the first practice, our proposed method enjoys linear complexity respecting to instance numbers, which is more applicable for large-scale IMVC tasks. Comprehensive experimental results on various benchmark datasets demonstrate the effectiveness and efficiency of our proposed algorithm against other IMVC competitors. The code is available at11https://github.com/wangsiwei2010/CVPR22-IMVC-CBG.

While classic video anomaly detection (VAD) requires labeled normal videos for training, emerging unsupervised VAD (UVAD) aims to discover anomalies directly from fully unlabeled videos. However, existing UVAD methods still rely on shallow models to perform detection or initialization, and they are evidently inferior to classic VAD methods. This paper proposes a full deep neural network (DNN) based solution that can realize highly effective UVAD. First, we, for the first time, point out that deep reconstruction can be surprisingly effective for UVAD, which inspires us to unveil a property named “normality advantage”, i.e., normal events will enjoy lower reconstruction loss when DNN learns to reconstruct unlabeled videos. With this property, we propose Localization based Reconstruction (LBR) as a strong UVAD baseline and a solid foundation of our solution. Second, we propose a novel self-paced refinement (SPR) scheme, which is synthesized into LBR to conduct UVAD. Unlike ordinary self-paced learning that injects more samples in an easy-to-hard manner, the proposed SPR scheme gradually drops samples so that suspicious anomalies can be removed from the learning process. In this way, SPR consolidates normality advantage and enables better UVAD in a more proactive way. Finally, we further design a variant solution that explicitly takes the motion cues into account. The solution evidently enhances the UVAD performance, and it sometimes even surpasses the best classic VAD methods. Experiments show that our solution not only significantly outperforms existing UVAD methods by a wide margin (5% to 9% AUROC), but also enables UVAD to catch up with the mainstream performance of classic VAD.

Online Event-based social networks (EBSNs), such as Meetup and Whova, which provide platforms for users to publish, arrange and participate in events, have become increasingly popular. A major challenge for managing EBSNs is to generate the most satisfactory event arrangement. Existing approaches usually focus on assigning a set of events organized to time intervals, but ignore the competitive relationships among different event organizers, which will lead to event time allocations unacceptable to organizers. Thus, a more intelligent EBSNs platform that allocates social events properly in a global view (i.e. the perspective of platform) is desired. In this work, we first formally define the problem of Platform-oriented Event Time Allocation (PETA), which contains two parts: the prediction of event feasible time period and the event time allocation. We propose a method to calculate event feasible time period based on event time prediction, and design a greedy algorithm and two approximation algorithms to solve the PETA problem. Extensive experiments on both real and synthetic datasets demonstrate that the proposed algorithms have high effectiveness and efficiency.

Attributed graph clustering is a basic yet essential method for graph data exploration. Recent efforts over graph contrastive learning have achieved impressive clustering performance. However, we observe that the commonly adopted InfoMax operation tends to capture redundant information, limiting the downstream clustering performance. To this end, we develop a novel method termed attributed graph clustering with dual redundancy reduction (AGC-DRR) to reduce the information redundancy in both input space and latent feature space. Specifically, for the input space redundancy reduction, we introduce an adversarial learning mechanism to adaptively learn a redundant edge-dropping matrix to ensure the diversity of the compared sample pairs. To reduce the redundancy in the latent space, we force the correlation matrix of the cross-augmentation sample embedding to approximate an identity matrix. Consequently, the learned network is forced to be robust against perturbation while discriminative against different samples. Extensive experiments have demonstrated that AGC-DRR outperforms the state-of-the-art clustering methods on most of our benchmarks. The corresponding code is available at https://github.com/gongleii/AGC-DRR.

Representation learning on the attribute-missing graphs, whose connection information is complete while the attribute information of some nodes is missing, is an important yet challenging task. To impute the missing attributes, existing methods isolate the learning processes of attribute and structure information embeddings, and force both resultant representations to align with a common in-discriminative normal distribution, leading to inaccurate imputation. To tackle these issues, we propose a novel graph-oriented imputation framework called initializing then refining (ITR), where we first employ the structure information for initial imputation, and then leverage observed attribute and structure information to adaptively refine the imputed latent variables. Specifically, we first adopt the structure embeddings of attribute-missing samples as the embedding initialization, and then refine these initial values by aggregating the reliable and informative embeddings of attribute-observed samples according to the affinity structure. Specially, in our refining process, the affinity structure is adaptively updated through iterations by calculating the sample-wise correlations upon the recomposed embeddings. Extensive experiments on four benchmark datasets verify the superiority of ITR against state-of-the-art methods.

With the increase of multimedia applications, data are often collected from multiple sensors or modalities, encouraging the rapid development of multi-view (also called multi modal) clustering technique. As a representative, late fusion multi-view clustering algorithm has attracted extensive attention due to its low computation complexity yet promising performance. However, most of them deal with the clustering problem in which all data views are available in advance, and overlook the scenarios where data observations of new views are accumulated over time. To solve this issue, we propose a continual approach on the basis of late fusion multi-view clustering framework. In specific, it only needs to maintain a consensus partition matrix and update knowledge with the incoming one of a new data view rather than keep all of them. This benefits a lot by preventing the previously learned knowledge from recomputing over and over again, saving a large amount of computation resource/time and labor force. Nevertheless, we design an alternate and convergent strategy to solve the resultant optimization problem. Also, the proposed algorithm shows excellent clustering performance and time/space efficiency in the experiment.

With pure normal training videos, video abnormal event detection (VAD) aims to build a normality model, and then detect abnormal events that deviate from this model. Despite of some progress, existing VAD methods typically train the normality model by a low-level learning objective (e.g. pixel-wise reconstruction/prediction), which often overlooks the high-level semantics in videos. To better exploit high-level semantics for VAD, we propose a novel paradigm that performs VAD by learning a Consistency-Aware high-level Feature Extractor (CAFE). Specifically, with a pre-trained deep neural network (DNN) as teacher network, we first feed raw video events into the teacher network and extract the outputs of multiple hidden layers as their high-level features, which contain rich high-level semantics. Guided by high-level features extracted from normal training videos, we train a student network to be the high-level feature extractor of normal events, so as to explicitly consider high-level semantics in training. For inference, a video event can be viewed as normal if the student extractor produces similar high-level features to the teacher network. Second, based on the fact that consecutive video frames usually enjoy minor differences, we propose a consistency-aware scheme that requires high-level features extracted from neighboring frames to be consistent. Our consistency-aware scheme not only encourages the student extractor to ignore low-level differences and capture more high-level semantics, but also enables better anomaly scoring. Last, we also design a generic framework that can bridge high-level and low-level learning in VAD to further ameliorate VAD performance. By flexibly embedding one or more low-level learning objectives into CAFE, the framework makes it possible to combine the strengths of both high-level and low-level learning. The proposed method attains state-of-the-art results on commonly-used benchmark datasets.

A representative multiple kernel clustering (MKC) algorithm, termed simple multiple kernel k-means (SMKKM), is recently proposed to optimally mine useful information from a set of pre-specified kernels to improve clustering performance. Different from existing min-min learning framework, it puts a novel min-max optimization manner, which attracts considerable attention in related community. Despite achieving encouraged success, we observe that SMKKM only focuses on combination coefficients among kernels and ignores the relationship among the importance of different samples. As a result, it does not sufficiently consider different contributions of each sample to clustering, and thus cannot effectively obtain the "ideal" similarity structure, leading to unsatisfying performance. To address this issue, this paper proposes a novel sample weighted multiple kernel k-means via min-max optimization (SWMKKM), which sufficiently considers the sum of relationship between one sample and the others to represent the sample weights. Such a weighting criterion helps clustering algorithm pay more attention to samples with more positive effects on clustering and avoids unreliable overestimation for samples with poor quality. Based on SMKKM, we adopt a reduced gradient algorithm with proved convergence to solve the resultant optimization problem. Comprehensive experiments on multiple benchmark datasets demonstrate that our proposed SWMKKM dramatically improves the state-of-the-art MKC algorithms, verifying the effectiveness of our proposed sample weighting criterion.

Clustering is a representative unsupervised method widely applied in multi-modal and multi-view scenarios. Multiple kernel clustering (MKC) aims to group data by integrating complementary information from base kernels. As a representative, late fusion MKC first decomposes the kernels into orthogonal partition matrices, then learns a consensus one from them, achieving promising performance recently. However, these methods fail to consider the noise inside the partition matrix, preventing further improvement of clustering performance. We discover that the noise can be disassembled into separable dual parts, i.e. N-noise and C-noise (Null space noise and Column space noise). In this paper, we rigorously define dual noise and propose a novel parameter-free MKC algorithm by minimizing them. To solve the resultant optimization problem, we design an efficient two-step iterative strategy. To our best knowledge, it is the first time to investigate dual noise within the partition in the kernel space. We observe that dual noise will pollute the block diagonal structures and incur the degeneration of clustering performance, and C-noise exhibits stronger destruction than N-noise. Owing to our efficient mechanism to minimize dual noise, the proposed algorithm surpasses the recent methods by large margins.

Anchor enhanced multi-view late fusion clustering has attracted numerous researchers' attention for its high clustering accuracy and promising efficiency. However, in the existing methods, the anchor points are usually generated through sampling or linearly combining the samples within the datasets, which could result in enormous time consumption and limited representation capability. To solve the problem, in our method, we learn the view-specific anchor points by learning them directly. Specifically, in our method, we first reconstruct the partition matrix of each view through multiplying a view-specific anchor matrix by a consensus reconstruction matrix. Then, by maximizing the weighted alignment between the base partition matrix and its estimated version in each view, we learn the optimal anchor points for each view. In particular, unlike previous late fusion algorithms, which define anchor points as linear combinations of existing samples, we define anchor points as a series of orthogonal vectors that are directly learned through optimization, which expands the learning space of the anchor points. Moreover, based on the above design, the resultant algorithm has only linear complexity and no hyper-parameter. Experiments on $12$ benchmark kernel datasets and 5 large-scale datasets illustrate that the proposed Efficient Anchor Learning-based Multi-view Clustering (AL-MVC) algorithm achieves the state-of-the-art performance in both clustering performance and efficiency.

Multiple kernel clustering (MKC) is an important research topic that has been widely studied for decades. However, current methods still face two problems: inefficient when handling out-of-sample data points and lack of theoretical study of the stability and generalization of clustering. In this paper, we propose a novel method that can efficiently compute the embedding of out-of-sample data with a solid generalization guarantee. Specifically, we approximate the eigen functions of the integral operator associated with the linear combination of base kernel functions to construct low-dimensional embeddings of out-of-sample points for efficient multiple kernel clustering. In addition, we, for the first time, theoretically study the stability of clustering algorithms and prove that the single-view version of the proposed method has uniform stability as $\mathcal{O}\left(Kn^{-3/2}\right)$ and establish an upper bound of excess risk as $\widetilde{\mathcal{O}}\left(Kn^{-3/2}+n^{-1/2}\right)$, where $K$ is the cluster number and $n$ is the number of samples. We then extend the theoretical results to multiple kernel scenarios and find that the stability of MKC depends on kernel weights. As an example, we apply our method to a novel MKC algorithm termed SimpleMKKM and derive the upper bound of its excess clustering risk, which is tighter than the current results. Extensive experimental results validate the effectiveness and efficiency of the proposed method.

Multi-view anchor graph clustering selects representative anchors to avoid full pair-wise similarities and therefore reduce the complexity of graph methods. Although widely applied in large-scale applications, existing approaches do not pay sufficient attention to establishing correct correspondences between the anchor sets across views. To be specific, anchor graphs obtained from different views are not aligned column-wisely. Such an Anchor-Unaligned Problem (AUP) would cause inaccurate graph fusion and degrade the clustering performance. Under multi-view scenarios, generating correct correspondences could be extremely difficult since anchors are not consistent in feature dimensions. To solve this challenging issue, we propose the first study of the generalized and flexible anchor graph fusion framework termed Fast Multi-View Anchor-Correspondence Clustering (FMVACC). Specifically, we show how to find anchor correspondence with both feature and structure information, after which anchor graph fusion is performed column-wisely. Moreover, we theoretically show the connection between FMVACC and existing multi-view late fusion and partial view-aligned clustering, which further demonstrates our generality. Extensive experiments on seven benchmark datasets demonstrate the effectiveness and efficiency of our proposed method. Moreover, the proposed alignment module also shows significant performance improvement applying to existing multi-view anchor graph competitors indicating the importance of anchor alignment. Our code is available at \url{https://github.com/wangsiwei2010/NeurIPS22-FMVACC}.

Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. Existing solutions either rely on hand-crafted descriptors or supervised gait representation learning. This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID. Specifically, we first create self-supervision by learning to reconstruct unlabeled skeleton sequences reversely, which involves richer high-level semantics to obtain better gait representations. Other pretext tasks are also explored to further improve self-supervised learning. Second, inspired by the fact that motion's continuity endows adjacent skeletons in one skeleton sequence and temporally consecutive skeleton sequences with higher correlations (referred as locality in 3D skeleton data), we propose a locality-aware attention mechanism and a locality-aware contrastive learning scheme, which aim to preserve locality-awareness on intra-sequence level and inter-sequence level respectively during self-supervised learning. Last, with context vectors learned by our locality-aware attention mechanism and contrastive learning scheme, a novel feature named Constrastive Attention-based Gait Encodings (CAGEs) is designed to represent gait effectively. Empirical evaluations show that our approach significantly outperforms skeleton-based counterparts by 15-40 percent Rank-1 accuracy, and it even achieves superior performance to numerous multi-modal methods with extra RGB or depth information. Our codes are available at https://github.com/Kali-Hac/Locality-Awareness-SGE.

Albeit great success has been achieved in image defocus blur detection, there are still several unsolved challenges, e.g., interference of background clutter, scale sensitivity and missing boundary details of blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We first fuse the features from different layers of FCN as shallow features and semantic features, respectively. Then, the fused shallow features are propagated to deep layers for refining the details of detected defocus blur regions, and the fused semantic features are propagated to shallow layers to assist in better locating blur regions. The fusion and refinement are carried out recurrently. In order to narrow the gap between low-level and high-level features, we embed a feature adaptation module before feature propagating to exploit the complementary information as well as reduce the contradictory response of different feature layers. Since different feature channels are with different extents of discrimination for detecting blur regions, we design a channel attention module to select discriminative features for feature refinement. Finally, the output of each layer at last recurrent step are fused to obtain the final result. We collect a new dataset consists of various challenging images and their pixel-wise annotations for promoting further study. Extensive experiments on two commonly used datasets and our newly collected one are conducted to demonstrate both the efficacy and efficiency of DeFusionNet.

Incomplete multi-view clustering aims to exploit the information of multiple incomplete views to partition data into their clusters. Existing methods only utilize the pair-wise sample correlation and pair-wise view correlation to improve the clustering performance but neglect the high-order correlation of samples and that of views. To address this issue, we propose a high-order correlation preserved incomplete multi-view subspace clustering (HCP-IMSC) method which effectively recovers the missing views of samples and the subspace structure of incomplete multi-view data. Specifically, multiple affinity matrices constructed from the incomplete multi-view data are treated as a third-order low rank tensor with a tensor factorization regularization which preserves the high-order view correlation and sample correlation. Then, a unified affinity matrix can be obtained by fusing the view-specific affinity matrices in a self-weighted manner. A hypergraph is further constructed from the unified affinity matrix to preserve the high-order geometrical structure of the data with incomplete views. Then, the samples with missing views are restricted to be reconstructed by their neighbor samples under the hypergraph-induced hyper-Laplacian regularization. Furthermore, the learning of view-specific affinity matrices as well as the unified one, tensor factorization, and hyper-Laplacian regularization are integrated into a unified optimization framework. An iterative algorithm is designed to solve the resultant model. Experimental results on various benchmark datasets indicate the superiority of the proposed method. The code is implemented by using MATLAB R2018a and MindSpore library: https://github.com/ChangTang/HCP-IMSC.

Multi-view subspace clustering has attracted intensive attention to effectively fuse multi-view information by exploring appropriate graph structures. Although existing works have made impressive progress in clustering performance, most of them suffer from the cubic time complexity which could prevent them from being efficiently applied into large-scale applications. To improve the efficiency, anchor sampling mechanism has been proposed to select vital landmarks to represent the whole data. However, existing anchor selecting usually follows the heuristic sampling strategy, e.g. k -means or uniform sampling. As a result, the procedures of anchor selecting and subsequent subspace graph construction are separated from each other which may adversely affect clustering performance. Moreover, the involved hyper-parameters further limit the application of traditional algorithms. To address these issues, we propose a novel subspace clustering method termed Fast Parameter-free Multi-view Subspace Clustering with Consensus Anchor Guidance (FPMVS-CAG). Firstly, we jointly conduct anchor selection and subspace graph construction into a unified optimization formulation. By this way, the two processes can be negotiated with each other to promote clustering quality. Moreover, our proposed FPMVS-CAG is proved to have linear time complexity with respect to the sample number. In addition, FPMVS-CAG can automatically learn an optimal anchor subspace graph without any extra hyper-parameters. Extensive experimental results on various benchmark datasets demonstrate the effectiveness and efficiency of the proposed method against the existing state-of-the-art multi-view subspace clustering competitors. These merits make FPMVS-CAG more suitable for large-scale subspace clustering. The code of FPMVS-CAG is publicly available at https://github.com/wangsiwei2010/FPMVS-CAG.

Location prediction has attracted much attention due to its important role in many location-based services, including taxi services, route navigation, traffic planning, and location-based advertisements. Traditional methods only use spatial-temporal trajectory data to predict where a user will go next. The divorce of semantic knowledge from the spatial-temporal one inhibits our better understanding of users’ activities. Inspired by the architecture of Long Short Term Memory (LSTM), we design ST-LSTM, which draws on semantic trajectories to predict future locations. Semantic data add a new dimension to our study, increasing the accuracy of prediction. Since semantic trajectories are sparser than the spatial-temporal ones, we propose a strategic filling algorithm to solve this problem. In addition, as the prediction is based on the historical trajectories of users, the cold-start problem arises. We build a new virtual social network for users to resolve the issue. Experiments on two real-world datasets show that the performance of our method is superior to those of the baselines.

Multi-view spectral clustering can effectively reveal the intrinsic cluster structure among data by performing clustering on the learned optimal embedding across views. Though demonstrating promising performance in various applications, most of existing methods usually linearly combine a group of pre-specified first-order Laplacian matrices to construct the optimal Laplacian matrix, which may result in limited representation capability and insufficient information exploitation. Also, storing and implementing complex operations on the{$n\times n}$Laplacian matrices incurs intensive storage and computation complexity. To address these issues, this paper first proposes a multi-view spectral clustering algorithm that learns a high-order optimal neighborhood Laplacian matrix, and then extends it to the late fusion version for accurate and efficient multi-view clustering. Specifically, our proposed algorithm generates the optimal Laplacian matrix by searching the neighborhood of the linear combination of both the first-order and high-order base Laplacian matrices simultaneously. By this way, the representative capacity of the learned optimal Laplacian matrix is enhanced, which is helpful to better utilize the hidden high-order connection information among data, leading to improved clustering performance. We design an efficient algorithm with proved convergence to solve the resultant optimization problem. Extensive experimental results on nine datasets demonstrate the superiority of the proposed algorithm

Multiple kernel clustering (MKC) algorithm aims to group data into different categories by optimally integrating information from a group of pre-specified kernels. Though demonstrating superiorities in various applications, we observe that existing MKC algorithms usuallydo not sufficiently consider the local density around individual data samplesandexcessively limit the representation capacity of the learned optimal kernel, leading to unsatisfying performance. In this paper, we propose an algorithm, called optimal neighborhood MKC with adaptive local kernels (ON-ALK), to address the two issues. In specific, we construct adaptive local kernels to sufficiently consider the local density around individual data samples, where different numbers of neighbors are discriminatingly selected on each sample. Further, the proposed ON-ALK algorithm boosts the representation of the learned optimal kernel via relaxing it into the neighborhood area of weighted combination of the pre-specified kernels. To solve the resultant optimization problem, a three-step iterative algorithm is designed and theoretically proven to be convergent. After that, we also study the generalization bound of the proposed algorithm. Extensive experiments have been conducted to evaluate the clustering performance. As indicated, the algorithm significantly outperforms state-of-the-art methods in recent literatures on six challenging benchmark datasets, verifying its advantages and effectiveness.

Although demonstrating great success, previous multi-view unsupervised feature selection (MV-UFS) methods often construct a view-specific similarity graph and characterize the local structure of data within each single view. In such a way, the cross-view information could be ignored. In addition, they usually assume that different feature views are projected from a latent feature space while the diversity of different views cannot be fully captured. In this work, we resent a MV-UFS model via cross-view local structure preserved diversity and consensus learning, referred to as CvLP-DCL briefly. In order to exploit both the shared and distinguishing information across different views, we project each view into a label space, which consists of a consensus part and a view-specific part. Therefore, we regularize the fact that different views represent same samples. Meanwhile, a cross-view similarity graph learning term with matrix-induced regularization is embedded to preserve the local structure of data in the label space. By imposing the$l_{2,1}$-norm on the feature projection matrices for constraining row sparsity, discriminative features can be selected from different views. An efficient algorithm is designed to solve the resultant optimization problem and extensive experiments on six publicly datasets are conducted to validate the effectiveness of the proposed CvLP-DCL.

Multi-view clustering has attracted increasing attention in multimedia, machine learning and data mining communities. As one kind of the essential multi-view clustering algorithm, multi-view subspace clustering (MVSC) becomes more and more popular due to its strong ability to reveal the intrinsic low dimensional clustering structure hidden across views. Despite superior clustering performance in various applications, we observe that existing MVSC methodsdirectly fuse multi-view information in the similarity level by merging noisy affinity matrices; andisolate the processes of affinity learning, multi-view information fusion and clustering. Both factors may cause insufficient utilization of multi-view information, leading to unsatisfying clustering performance. This paper proposes a novel consensus one-step multi-view subspace clustering (COMVSC) method to address these issues. Instead of directly fusing multiple affinity matrices, COMVSC optimally integrates discriminative partition-level information, which is helpful to eliminate noise among data. Moreover, the affinity matrices, consensus representation and final clustering labels matrix are learned simultaneously in a unified framework. By doing so, the three steps can negotiate with each other to best serve the clustering task, leading to improved performance. Accordingly, we propose an iterative algorithm to solve the resulting optimization problem. Extensive experiment results on benchmark datasets demonstrate the superiority of our method against other state-of-the-art approaches.

Multi-view clustering, which exploits the multi-view information to partition data into their clusters, has attracted intense attention. However, most existing methods directly learn a similarity graph from original multi-view features, which inevitably contain noises and redundancy information. The learned similarity graph is inaccurate and is insufficient to depict the underlying cluster structure of multi-view data. To address this issue, we propose a novel multi-view clustering method that is able to construct an essential similarity graph in a spectral embedding space instead of the original feature space. Concretely, we first obtain multiple spectral embedding matrices from the view-specific similarity graphs, and reorganize the gram matrices constructed by the inner product of the normalized spectral embedding matrices into a tensor. Then, we impose a weighted tensor nuclear norm constraint on the tensor to capture high-order consistent information among multiple views. Furthermore, we unify the spectral embedding and low rank tensor learning into a unified optimization framework to determine the spectral embedding matrices and tensor representation jointly. Finally, we obtain the consensus similarity graph from the gram matrices via an adaptive neighbor manner. An efficient optimization algorithm is designed to solve the resultant optimization problem. Extensive experiments on six benchmark datasets are conducted to verify the efficacy of the proposed method. The code is implemented by using MATLAB R2018a and MindSpore library[1]:https://github.com/guanyuezhen/CGL.

Multiple kernel subspace clustering (MKSC), as an important extension for handling multi-view non-linear subspace data, has shown notable success in a wide variety of machine learning tasks. The key objective of MKSC is to build a flexible and appropriate graph for clustering from the kernel space. However, existing MKSC methods apply a mechanism utilizing the kernel trick to the traditional self-expressive principle, where the similarity graphs are built on the respective high-dimensional (or even infinite) reproducing kernel Hilbert space (RKHS). Regarding this strategy, we argue that the original high-dimensional spaces usually include noise and unreliable similarity measures and, therefore, output a low-quality graph matrix, which degrades clustering performance. In this paper, inspired by projective clustering, we propose the utilization of a complementary similarity graph by fusing the multiple kernel graphs constructed in the low-dimensional partition space, termed projective multiple kernel subspace clustering (PMKSC). By incorporating intrinsic structures with multi-view data, PMKSC alleviates the noise and redundancy in the original kernel space and obtains high-quality similarity to uncover the underlying clustering structures. Furthermore, we design a three-step alternate algorithm with proven convergence to solve the proposed optimization problem. The experimental results on ten multiple kernel benchmark datasets validate the effectiveness of our proposed PMKSC, compared to the state-of-the-art multiple kernel and kernel subspace clustering methods, by a large margin. Our code is available athttps://github.com/MengjingSun/PMKSC-code.

Taking the assumption that data samples are able to be reconstructed with the dictionary formed by themselves, recent multiview subspace clustering (MSC) algorithms aim to find a consensus reconstruction matrix via exploring complementary information across multiple views. Most of them directly operate on the original data observations without preprocessing, while others operate on the corresponding kernel matrices. However, they both ignore that the collected features may be designed arbitrarily and hard guaranteed to be independent and nonoverlapping. As a result, original data observations and kernel matrices would contain a large number of redundant details. To address this issue, we propose an MSC algorithm that groups samples and removes data redundancy concurrently. In specific, eigendecomposition is employed to obtain the robust data representation of low redundancy for later clustering. By utilizing the two processes into a unified model, clustering results will guide eigendecomposition to generate more discriminative data representation, which, as feedback, helps obtain better clustering results. In addition, an alternate and convergent algorithm is designed to solve the optimization problem. Extensive experiments are conducted on eight benchmarks, and the proposed algorithm outperforms comparative ones in recent literature by a large margin, verifying its superiority. At the same time, its effectiveness, computational efficiency, and robustness to noise are validated experimentally.

Matrix inversion frequently occurs in the fields of science, engineering, and related fields. Numerous matrix inversion schemes are often based on the premise that the solution procedure is ideal and noise-free. However, external interference is generally ubiquitous and unavoidable in practice. Therefore, an integrated-enhanced zeroing neural network (IEZNN) model has been proposed to handle the time-variant matrix inversion issue interfered with by noise. However, the IEZNN model can only deal with small time-variant noise interference. With slightly larger noise interference, the IEZNN model may not converge to the theoretical solution exactly. Therefore, a variable-parameter noise-tolerant zeroing neural network (VPNTZNN) model is proposed to overcome shortcomings and improve the inadequacy. Moreover, the excellent convergence and robustness of the VPNTZNN model are rigorously analyzed and proven. Finally, compared with the original zeroing neural network (OZNN) model and the IEZNN model for matrix inversion, numerical simulations and a practical application reveal that the proposed VPNTZNN model has the best robust property under the same external noise interference.

Current multiple kernel clustering algorithms compute a partition with the consensus kernel or graph learned from the pre-specified ones, while the emerging late fusion methods firstly construct multiple partitions from each kernel separately, and then obtain a consensus one with them. However, both of them directly distill the clustering information from kernels or graphs to partition matrices, where the sudden dimension drop would result in loss of advantageous details for clustering. In this paper, we provide a brief insight of the aforementioned issue and propose a hierarchical approach to perform clustering while preserving advantageous details maximumly. Specifically, we gradually group samples into fewer clusters, together with generating a sequence of intermediary matrices of descending sizes. The consensus partition with is simultaneously learned and conversely guides the construction of intermediary matrices. Nevertheless, this cyclic process is modeled into an unified objective and an alternative algorithm is designed to solve it. In addition, the proposed method is validated and compared with other representative multiple kernel clustering algorithms on benchmark datasets, demonstrating state-of-the-art performance by a large margin.

Deep clustering is a fundamental yet challenging task for data analysis. Recently we witness a strong tendency of combining autoencoder and graph neural networks to exploit structure information for clustering performance enhancement. However, we observe that existing literature 1) lacks a dynamic fusion mechanism to selectively integrate and refine the information of graph structure and node attributes for consensus representation learning; 2) fails to extract information from both sides for robust target distribution (i.e., “groundtruth” soft labels) generation. To tackle the above issues, we propose a Deep Fusion Clustering Network (DFCN). Specifically, in our network, an interdependency learning-based Structure and Attribute Information Fusion (SAIF) module is proposed to explicitly merge the representations learned by an autoencoder and a graph autoencoder for consensus representation learning. Also, a reliable target distribution generation measure and a triplet self-supervision strategy, which facilitate cross-modality information exploitation, are designed for network training. Extensive experiments on six benchmark datasets have demonstrated that the proposed DFCN consistently outperforms the state-of-the-art deep clustering methods.

Existing non-negative matrix factorization based multi-view clustering algorithms compute multiple coefficient matrices respect to different data views, and learn a common consensus concurrently. The final partition is always obtained from the consensus with classical clustering techniques, such as k-means. However, the non-negativity constraint prevents from obtaining a more discriminative embedding. Meanwhile, this two-step procedure fails to unify multi-view matrix factorization with partition generation closely, resulting in unpromising performance. Therefore, we propose an one-pass multi-view clustering algorithm by removing the non-negativity constraint and jointly optimize the aforementioned two steps. In this way, the generated partition can guide multi-view matrix factorization to produce more purposive coefficient matrix which, as a feedback, improves the quality of partition. To solve the resultant optimization problem, we design an alternate strategy which is guaranteed to be convergent theoretically. Moreover, the proposed algorithm is free of parameter and of linear complexity, making it practical in applications. In addition, the proposed algorithm is compared with recent advances in literature on benchmarks, demonstrating its effectiveness, superiority and efficiency.

As a representative of multiple kernel clustering (MKC), simple multiple kernel k-means (SimpleMKKM) is recently put forward to boosting the clustering performance by optimally fusing a group of pre-specified kernel matrices. Despite achieving significant improvement in a variety of applications, we find out that SimpleMKKM could indiscriminately force all sample pairs to be equally aligned with the same ideal similarity. As a result, it does not sufficiently take the variation of samples into consideration, leading to unsatisfying clustering performance. To address these issues, this paper proposes a novel MKC algorithm with a "local" kernel alignment, which only requires that the similarity of a sample to its k-nearest neighbours be aligned with the ideal similarity matrix. Such an alignment helps the clustering algorithm to focus on closer sample pairs that shall stay together and avoids involving unreliable similarity evaluation for farther sample pairs. After that, we theoretically show that the objective of SimpleMKKM is a special case of this local kernel alignment criterion with normalizing each base kernel matrix. Based on this observation, the proposed localized SimpleMKKM can be readily implemented by existing SimpleMKKM package. Moreover, we conduct extensive experiments on several widely used benchmark datasets to evaluate the clustering performance of localized SimpleMKKM. The experimental results have demonstrated that our algorithm consistently outperforms the state-of-the-art ones, verifying the effectiveness of the proposed local kernel alignment criterion. The code of Localized SimpleMKKM is publicly available at: https://github.com/xinwangliu/LocalizedSMKKM.

In this paper, we propose a novel incomplete multi-view clustering method, in which a tensor nuclear norm regularizer elegantly diffuses the information of multi-view block-diagonal structure across different views. By exploring the membership between observed and missing samples and that between missing ones in each incomplete view with the guidance of the high-order view consistency, a global block-diagonal structure is well preserved in multiple spectral embedding matrices. Meanwhile, a consensus representation with strong separability is obtained for clustering. An iterative algorithm based on Augmented Lagrange Multiplier (ALM) is designed to solve the resultant model. Experimental results on six benchmark datasets indicate the superiority of the proposed method. http://github.com/ChangTang/TMBSD

Existing late fusion multi-view clustering (LFMVC) optimally integrates a group of pre-specified base partition matrices to learn a consensus one. It is then taken as the input of the widely used k-means to generate the cluster labels. As observed, the learning of the consensus partition matrix and the generation of cluster labels are separately done. These two procedures lack necessary negotiation and can not best serve for each other, which may adversely affect the clustering performance. To address this issue, we propose to unify the aforementioned two learning procedures into a single optimization, in which the consensus partition matrix can better serve for the generation of cluster labels, and the latter is able to guide the learning of the former. To optimize the resultant optimization problem, we develop a four-step alternate algorithm with proved convergence. We theoretically analyze the clustering generalization error of the proposed algorithm on unseen data. Comprehensive experiments on multiple benchmark datasets demonstrate the superiority of our algorithm in terms of both clustering accuracy and computational efficiency. It is expected that the simplicity and effectiveness of our algorithm will make it a good option to be considered for practical multi-view clustering applications.

In this paper, we propose a hyperspectral band selection method via spatial-spectral weighted region-wise multiple graph fusion-based spectral clustering, referred to as RMGF briefly. Considering that different objects have different reflection characteristics, we use a superpixel segmentation algorithm to segment the first principal component of original hyperspectral image cube into homogeneous regions. For each superpixel, we construct a corresponding similarity graph to reflect the similarity between band pairs. Then, a multiple graph diffusion strategy with theoretical convergence guarantee is designed to learn a unified graph for partitioning the whole hyperspectral cube into several subcubes via spectral clustering. During the graph diffusion process, the spatial and spectral information of each superpixel are embedded to make spatial/spectral similar superpixels contribute more to each other. Finally, the band containing minimum noise in each subcube is selected to represent the whole subcube. Extensive experiments are conducted on three public datasets to validate the superiority of the proposed method when compared with other state-of-the-art ones.

Incomplete multi-view clustering is an important research topic in multimedia where partial data entries of one or more views are missing. Current subspace clustering approaches mostly employ matrix factorization on the observed feature matrices to address this issue. Meanwhile, self-representation technique is left unexplored, since it explicitly relies on full data entries to construct the coefficient matrix, which is contradictory to the incomplete data setting. However, it is widely observed that self-representation subspace method enjoys a better clustering performance over the factorization based one. Therefore, we adapt it to incomplete data by jointly performing data imputation and self-representation learning. To the best of our knowledge, this is the first attempt in incomplete multi-view clustering literature. Besides, the proposed method is carefully compared with current advances in experiment with respect to different missing ratios, verifying its effectiveness.

Multi-view subspace clustering has received widespread attention to effectively fuse multi-view information among multimedia applications. Considering that most existing approaches' cubic time complexity makes it challenging to apply to realistic large-scale scenarios, some researchers have addressed this challenge by sampling anchor points to capture distributions in different views. However, the separation of the heuristic sampling and clustering process leads to weak discriminate anchor points. Moreover, the complementary multi-view information has not been well utilized since the graphs are constructed independently by the anchors from the corresponding views. To address these issues, we propose a Scalable Multi-view Subspace Clustering with Unified Anchors (SMVSC). To be specific, we combine anchor learning and graph construction into a unified optimization framework. Therefore, the learned anchors can represent the actual latent data distribution more accurately, leading to a more discriminative clustering structure. Most importantly, the linear time complexity of our proposed algorithm allows the multi-view subspace clustering approach to be applied to large-scale data. Then, we design a four-step alternative optimization algorithm with proven convergence. Compared with state-of-the-art multi-view subspace clustering methods and large-scale oriented methods, the experimental results on several datasets demonstrate that our SMVSC method achieves comparable or better clustering performance much more efficiently. The code of SMVSC is available at https://github.com/Jeaninezpp/SMVSC.

As a representative of multi-view clustering (MVC), late fusion MVC (LF-MVC) algorithm has attracted intensive attention due to its superior clustering accuracy and high computational efficiency. One common assumption adopted by existing LF-MVC algorithms is that all views of each sample are available. However, it is widely observed that there are incomplete views for partial samples in practice. In this paper, we propose One-Stage Late Fusion Incomplete Multi-view Clustering (OS-LF-IMVC) to address this issue. Specifically, we propose to unify the imputation of incomplete views and the clustering task into a single optimization procedure, so that the learning of the consensus partition matrix can directly assist the final clustering task. To optimize the resultant optimization problem, we develop a five-step alternate strategy with theoretically proved convergence. Comprehensive experiments on multiple benchmark datasets are conducted to demonstrate the efficiency and effectiveness of the proposed OS-LF-IMVC algorithm.

Multi-view clustering (MVC) has been extensively studied to collect multiple source information in recent years. One typical type of MVC methods is based on matrix factorization to effectively perform dimension reduction and clustering. However, the existing approaches can be further improved with following considerations: i) The current one-layer matrix factorization framework cannot fully exploit the useful data representations. ii) Most algorithms only focus on the shared information while ignore the view-specific structure leading to suboptimal solutions. iii) The partition level information has not been utilized in existing work. To solve the above issues, we propose a novel multi-view clustering algorithm via deep matrix decomposition and partition alignment. To be specific, the partition representations of each view are obtained through deep matrix decomposition, and then are jointly utilized with the optimal partition representation for fusing multi-view information. Finally, an alternating optimization algorithm is developed to solve the optimization problem with proven convergence. The comprehensive experimental results conducted on six benchmark multi-view datasets clearly demonstrates the effectiveness of the proposed algorithm against the SOTA methods. The code address for this algorithm is https://github.com/ZCtalk/MVC-DMF-PA.

Deep autoencoder-based methods are the majority of deep anomaly detection. An autoencoder learning on training data is assumed to produce higher reconstruction error for the anomalous samples than the normal samples and thus can distinguish anomalies from normal data. However, this assumption does not always hold in practice, especially in unsupervised anomaly detection, where the training data is anomaly contaminated. We observe that the autoencoder generalizes so well on the training data that it can reconstruct both the normal data and the anomalous data well, leading to poor anomaly detection performance. Besides, we find that anomaly detection performance is not stable when using reconstruction error as anomaly score, which is unacceptable in the unsupervised scenario. Because there are no labels to guide on selecting a proper model. To mitigate these drawbacks for autoencoder-based anomaly detection methods, we propose an Improved AutoEncoder for unsupervised Anomaly Detection (IAEAD). Specifically, we manipulate feature space to make normal data points closer using anomaly detection-based loss as guidance. Different from previous methods, by integrating the anomaly detection-based loss and autoencoder's reconstruction loss, IAEAD can jointly optimize for anomaly detection tasks and learn representations that preserve the local data structure to avoid feature distortion. Experiments on five image data sets empirically validate the effectiveness and stability of our method.

Multiview clustering (MVC) collects complementary and abundant information, which draws much attention in machine learning and data mining community. Existing MVC methods usually hold the assumption that all the views are complete. However, multiple source data are often incomplete in real-world applications, and so on sensor failure or unfinished collection process, which gives rise to incomplete multiview clustering (IMVC). Although enormous efforts have been devoted in IMVC, there still are some urgent issues that need to be solved: (i) The locality among multiple views has not been utilized in the existing mechanism; (ii) Existing methods inappropriately force all the views to share consensus representation while ignoring specific structures. In this paper, we propose a novel method termed partial MVC with locality graph regularization to address these issues. First, followed the traditional IMVC approaches, we construct weighted semi-nonnegative matrix factorization models to handle incomplete multiview data. Then, upon the consensus representation matrix, the locality graph is constructed for regularizing the shared feature matrix. Moreover, we add the coefficient regression term to constraint the various base matrices among views. We incorporate the three aforementioned processes into a unified framework, whereas they can negotiate with each other serving for learning tasks. An effective iterative algorithm is proposed to solve the resultant optimization problem with theoretically guaranteed convergence. The comprehensive experiment results on several benchmarks demonstrate the effectiveness of the proposed method.

Multiple kernel clustering (MKC) methods aim at integrating an optimal partition from a set of precalculated kernel matrices. Though achieving success in various applications, we observe that existing MKC methods: (i) lack of representation flexibility; and (ii) do not considerably preserve the locality structure in partition space. These issues may adversely affect the learning procedure of MKC, leading to unsatisfying clustering performance. In this paper, we propose a late fusion MKC method with local graph refinement to address the aforementioned issues. Different from existing MKC mechanisms, our method unifies the traditional weighted multiple kernel k-means, kernel partition, and graph construction into a single optimization procedure. The local graph is utilized to preserve the locality information in partition space and therefore all of the counterparts can be boosted for mutual clustering improvements. By this way, our approach enhances the local graph structure in partition space and enjoys more flexible kernel representations, leading to significant clustering improvements. Moreover, a three-step alternate algorithm is developed to solve the resultant optimization problem with proved convergence. Extensive experiments are conducted on several multiple kernel benchmark datasets to compare the proposed algorithm with the state-of-the-art ones, and the results well demonstrate its effectiveness and superiority.

Incomplete multi-view clustering (IMVC) optimally combines multiple pre-specified incomplete views to improve clustering performance. Among various excellent solutions, the recently proposed multiple kernel k-means with incomplete kernels (MKKM-IK) forms a benchmark, which redefines IMVC as a joint optimization problem where the clustering and kernel matrix imputation tasks are alternately performed until convergence. Though demonstrating promising performance in various applications, we observe that the manner of kernel matrix imputation in MKKM-IK would incur intensive computational and storage complexities, over-complicated optimization and limitedly improved clustering performance. In this paper, we first propose an Efficient and Effective Incomplete Multi-view Clustering (EE-IMVC) algorithm to address these issues. Instead of completing the incomplete kernel matrices, EE-IMVC proposes to impute each incomplete base matrix generated by incomplete views with a learned consensus clustering matrix. Moreover, we further improve this algorithm by incorporating prior knowledge to regularize the learned consensus clustering matrix. Two three-step iterative algorithms are carefully developed to solve the resultant optimization problems with linear computational complexity, and their convergence is theoretically proven. After that, we theoretically study the generalization bound of the proposed algorithms. Furthermore, we conduct comprehensive experiments to study the proposed algorithms in terms of clustering accuracy, evolution of the learned consensus clustering matrix and the convergence. As indicated, our algorithms deliver their effectiveness by significantly and consistently outperforming some state-of-the-art ones.

Multi-instance learning (MIL) has been extensively applied to various real tasks involving objects with bags of instances, such as in drugs and images. Previous studies on MIL assume that data are entirely complete. However, in many real tasks, the instance is fragmentary. In this article, we present probably the first study on multi-instance classification with fragmentary data. In our proposed framework, called fragmentary multi-instance classification (FIC), the fragmentary data are completed and the multi-instance classifier is learned jointly. To facilitate the integration between the completion and classifier learning, FIC establishes the weighting mechanism to measure the importance levels of different instances. To validate the compatibility of our framework, four typical MIL methods, including multi-instance support vector machine (MI-SVM), expectation maximization diverse density (EM-DD), citation- K nearest neighbors (Citation-KNNs), and MIL with discriminative bag mapping (MILDM), are embedded into the framework to obtain the corresponding FIC versions. As an illustration, an efficient solving algorithm is developed to address the problem for MI-SVM, together with the proof of convergence behavior. The experimental results on various types of real-world datasets demonstrate the effectiveness.

Recently, convex-concave bilinear Saddle Point Problems (SPP) is widely used in lasso problems, Support Vector Machines, game theory, and so on. Previous researches have proposed many methods to solve SPP, and present their convergence rate theoretically. To achieve linear convergence, analysis in those previouse studies requires strong convexity of φ( z ). But, we find the linear convergence can also be achieved even for a general convex but not strongly convex φ( z ). In the article, by exploiting the strong duality of SPP, we propose a new method to solve SPP, and achieve the linear convergence. We present a new general sufficient condition to achieve linear convergence, but do not require the strong convexity of φ( z ). Furthermore, a more efficient method is also proposed, and its convergence rate is analyzed in theoretical. Our analysis shows that the well conditioned φ( z ) is necessary to improve the efficiency of our method. Finally, we conduct extensive empirical studies to evaluate the convergence performance of our methods.

Similarity representation plays a central role in increasingly popular anomaly detection techniques, which have been successfully applied in various realistic scenes. Until now, many low-rank representation techniques have been introduced to measure the similarity relations of data; yet, they only concern to minimize reconstruction errors, without involving the structural information of data. Besides, the traditional low-rank representation methods often take nuclear norm as their low-rank constraints, easily yielding a suboptimal solution. To address the problems above, in this article, we propose a novel anomaly detection method, which exploits kernel preserving embedding, as well as the double nuclear norm, to explore the similarity relations of data. Based on the similarity relations, a kind of probability transition matrix is derived, and a tailored random walk is further adopted to reveal anomalies. The proposed method can not only preserve the manifold structural properties of the data, but also alleviate the suboptimal problem. To validate the superiority of our method, extensive experiments with eight popular anomaly detection algorithms were conducted on 12 widely used datasets. The experimental results show that our detection method outperformed the state-of-the-art anomaly detection algorithms in most cases.

Simultaneous clustering and optimization (SCO) has recently drawn much attention due to its wide range of practical applications. Many methods have been previously proposed to solve this problem and obtain the optimal model. However, when a dataset evolves over time, those existing methods have to update the model frequently to guarantee accuracy; such updating is computationally infeasible. In this paper, we propose a new formulation of SCO to handle evolving datasets. Specifically, we propose a new variant of the alternating direction method of multipliers (ADMM) to solve this problem efficiently. The guarantee of model accuracy is analyzed theoretically for two specific tasks: ridge regression and convex clustering. Extensive empirical studies confirm the effectiveness of our method.

Due to the remarkable potential applications, defocus blur detection, which aims to separate blurry regions from an image, has attracted much attention. Although significant progress has been made by many methods, there are still various challenges that hinder the results, e.g., confusing background areas, sensitivity to the scale and missing the boundary details of the defocus blur regions. To solve these issues, in this paper, we propose a deep convolutional neural network (CNN) for defocus blur detection via a Bi-directional Residual Refining network (BR2Net). Specifically, a residual learning and refining module (RLRM) is designed to correct the prediction errors in the intermediate defocus blur map. Then, we develop a bidirectional residual feature refining network with two branches by embedding multiple RLRMs into it for recurrently combining and refining the residual features. One branch of the network refines the residual features from the shallow layers to the deep layers, and the other branch refines the residual features from the deep layers to the shallow layers. In such a manner, both the low-level spatial details and highlevel semantic information can be encoded step by step in two directions to suppress background clutter and enhance the detected region details. The outputs of the two branches are fused to generate the final results. In addition, with the observation that different feature channels have different extents of discrimination for detecting blurred regions, we add a channel attention module to each feature extraction layer to select more discriminative features for residual learning. To promote further research on defocus blur detection, we create a new dataset with various challenging images and manually annotate their corresponding pixelwise ground truths. The proposed network is validated on two commonly used defocus blur detection datasets and our newly collected dataset by comparing it with 10 other state-of-the-art methods. Extensive experiments with ablation studies demonstrate that BR2Net consistently and significantly outperforms the competitors in terms of both the efficiency and accuracy.

The clustering ensemble has emerged as an important extension of the classical clustering problem. It provides an elegant framework to integrate multiple weak base clusterings to generate a strong consensus result. Most existing clustering ensemble methods usually exploit all data to learn a consensus clustering result, which does not sufficiently consider the adverse effects caused by some difficult instances. To handle this problem, we propose a novel self-paced clustering ensemble (SPCE) method, which gradually involves instances from easy to difficult ones into the ensemble learning. In our method, we integrate the evaluation of the difficulty of instances and ensemble learning into a unified framework, which can automatically estimate the difficulty of instances and ensemble the base clusterings. To optimize the corresponding objective function, we propose a joint learning algorithm to obtain the final consensus clustering result. Experimental results on benchmark data sets demonstrate the effectiveness of our method.

As a class of batch-mode reinforcement learning (RL) methods for Markov decision problems with large or continuous state spaces, approximate policy iteration (API) has received increasing attention in the past decades. One open problem in the design of API algorithms is how to construct the basis functions or features for value function approximation (VFA). In this paper, we propose a novel batch-mode RL approach with randomly projected features for VFA. The proposed approach can be viewed as an extension of extreme learning machines (ELMs) to RL problems so it can be called ELM-API. The ELMs have been popularly studied in supervised learning problems, but there is not much work on the extension of ELMs to learning control problems. The proposed approach has advantages over the previous API algorithms in that the features for VFA can be quickly generated without complex parameter selection and the performance will be adaptive to different sample sets in batch-mode RL. In particular, the ELM-API approach can realize fast and efficient feature reconstruction when training sample sets are relatively small. Comprehensive simulation studies on two benchmark learning control problems were carried out to test the performance of API algorithms with different feature construction methods. It is shown that the ELM-API algorithm can obtain comparable or better performance than the previous API approaches. To further show the effectiveness of ELM-API in real-world applications, the simulation results on a more challenging high-dimensional lane-changing decision problem in dynamic traffic environment are also reported, which show the capability of the ELM-API algorithm in learning satisfactory lane-changing policies with high data efficiency.

Graph based multi-view clustering has been paid great attention by exploring the neighborhood relationship among data points from multiple views. Though achieving great success in various applications, we observe that most of previous methods learn a consensus graph by building certain data representation models, which at least bears the following drawbacks. First, their clustering performance highly depends on the data representation capability of the model. Second, solving these resultant optimization models usually results in high computational complexity. Third, there are often some hyper-parameters in these models need to tune for obtaining the optimal results. In this work, we propose a general, effective and parameter-free method with convergence guarantee to learn a unified graph for multi-view data clustering via cross-view graph diffusion (CGD), which is the first attempt to employ diffusion process for multi-view clustering. The proposed CGD takes the traditional predefined graph matrices of different views as input, and learns an improved graph for each single view via an iterative cross diffusion process by 1) capturing the underlying manifold geometry structure of original data points, and 2) leveraging the complementary information among multiple graphs. The final unified graph used for clustering is obtained by averaging the improved view associated graphs. Extensive experiments on several benchmark datasets are conducted to demonstrate the effectiveness of the proposed method in terms of seven clustering evaluation metrics.

Defocus blur detection aims to separate the in-focus and out-of-focus regions in an image. Although attracting more and more attention due to its remarkable potential applications, there are still several challenges for accurate defocus blur detection, such as the interference of background clutter, sensitivity to scales and missing boundary details of defocus blur regions. In order to address these issues, we propose a deep neural network which Recurrently Refines Multi-scale Residual Features (R2MRF) for defocus blur detection. We firstly extract multi-scale deep features by utilizing a fully convolutional network. For each layer, we design a novel recurrent residual refinement branch embedded with multiple residual refinement modules (RRMs) to more accurately detect blur regions from the input image. Considering that the features from bottom layers are able to capture rich low-level features for details preservation while the features from top layers are capable of characterizing the semantic information for locating blur regions, we aggregate the deep features from different layers to learn the residual between the intermediate prediction and the ground truth for each recurrent step in each residual refinement branch. Since the defocus degree is sensitive to image scales, we finally fuse the side output of each branch to obtain the final blur detection map. We evaluate the proposed network on two commonly used defocus blur detection benchmark datasets by comparing it with other 11 state-of-the-art methods. Extensive experimental results with ablation studies demonstrate that R2MRF consistently and significantly outperforms the competitors in terms of both efficiency and accuracy.

Multi-view spectral clustering aims to group data into different categories by optimally exploring complementary information from multiple Laplacian matrices. However, existing methods usually linearly combine a group of pre-specified first-order Laplacian matrices to construct an optimal Laplacian matrix, which may result in limited representation capability and insufficient information exploitation. In this paper, we propose a novel optimal neighborhood multi-view spectral clustering (ONMSC) algorithm to address these issues. Specifically, the proposed algorithm generates an optimal Laplacian matrix by searching the neighborhood of both the linear combination of the first-order and high-order base Laplacian matrices simultaneously. This design enhances the representative capacity of the optimal Laplacian and better utilizes the hidden high-order connection information, leading to improved clustering performance. An efficient algorithm with proved convergence is designed to solve the resultant optimization problem. Extensive experimental results on 9 datasets demonstrate the superiority of our algorithm against state-of-the-art methods, which verifies the effectiveness and advantages of the proposed ONMSC.

Abstract Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

Multiple kernel learning (MKL) has been intensively studied during the past decade. It optimally combines the multiple channels of each sample to improve classification performance. However, existing MKL algorithms cannot effectively handle the situation where some channels of the samples are missing, which is not uncommon in practical applications. This paper proposes three absent MKL (AMKL) algorithms to address this issue. Different from existing approaches where missing channels are first imputed and then a standard MKL algorithm is deployed on the imputed data, our algorithms directly classify each sample based on its observed channels, without performing imputation. Specifically, we define a margin for each sample in its own relevant space, a space corresponding to the observed channels of that sample. The proposed AMKL algorithms then maximize the minimum of all sample-based margins, and this leads to a difficult optimization problem. We first provide two two-step iterative algorithms to approximately solve this problem. After that, we show that this problem can be reformulated as a convex one by applying the representer theorem. This makes it readily be solved via existing convex optimization packages. In addition, we provide a generalization error bound to justify the proposed AMKL algorithms from a theoretical perspective. Extensive experiments are conducted on nine UCI and six MKL benchmark datasets to compare the proposed algorithms with existing imputation-based methods. As demonstrated, our algorithms achieve superior performance and the improvement is more significant with the increase of missing ratio.

Multiple kernel clustering (MKC) algorithms optimally combine a group of pre-specified base kernel matrices to improve clustering performance. However, existing MKC algorithms cannot efficiently address the situation where some rows and columns of base kernel matrices are absent. This paper proposes two simple yet effective algorithms to address this issue. Different from existing approaches where incomplete kernel matrices are first imputed and a standard MKC algorithm is applied to the imputed kernel matrices, our first algorithm integrates imputation and clustering into a unified learning procedure. Specifically, we perform multiple kernel clustering directly with the presence of incomplete kernel matrices, which are treated as auxiliary variables to be jointly optimized. Our algorithm does not require that there be at least one complete base kernel matrix over all the samples. Also, it adaptively imputes incomplete kernel matrices and combines them to best serve clustering. Moreover, we further improve this algorithm by encouraging these incomplete kernel matrices to mutually complete each other. The three-step iterative algorithm is designed to solve the resultant optimization problems. After that, we theoretically study the generalization bound of the proposed algorithms. Extensive experiments are conducted on 13 benchmark data sets to compare the proposed algorithms with existing imputation-based methods. Our algorithms consistently achieve superior performance and the improvement becomes more significant with increasing missing ratio, verifying the effectiveness and advantages of the proposed joint imputation and clustering.

As a metric to measure the performance of an online method, dynamic regret with switching cost has drawn much attention for online decision making problems. Although the sublinear regret has been provided in much previous research, we still have little knowledge about the relation between the dynamic regret and the switching cost . In the article, we investigate the relation for two classic online settings: Online Algorithms (OA) and Online Convex Optimization (OCO). We provide a new theoretical analysis framework that shows an interesting observation; that is, the relation between the switching cost and the dynamic regret is different for settings of OA and OCO. Specifically, the switching cost has significant impact on the dynamic regret in the setting of OA. But it does not have an impact on the dynamic regret in the setting of OCO. Furthermore, we provide a lower bound of regret for the setting of OCO, which is same with the lower bound in the case of no switching cost. It shows that the switching cost does not change the difficulty of online decision making problems in the setting of OCO.

Deep clustering gains superior performance than conventional clustering by jointly performing feature learning and cluster assignment. Although numerous deep clustering algorithms have emerged in various applications, most of them fail to learn robust cluster-oriented features which in turn hurts the final clustering performance. To solve this problem, we propose a two-stage deep clustering algorithm by incorporating data augmentation and self-paced learning. Specifically, in the first stage, we learn robust features by training an autoencoder with examples that are augmented by random shifting and rotating the given clean examples. Then, in the second stage, we encourage the learned features to be cluster-oriented by alternatively finetuning the encoder with the augmented examples and updating the cluster assignments of the clean examples. During finetuning the encoder, the target of each augmented example in the loss function is the center of the cluster to which the clean example is assigned. The targets may be computed incorrectly, and the examples with incorrect targets could mislead the encoder network. To stabilize the network training, we select most confident examples in each iteration by utilizing the adaptive self-paced learning. Extensive experiments validate that our algorithm outperforms the state of the arts on four image datasets.

Feature extraction and feature selection have been regarded as two independent dimensionality reduction methods in most of the existing literature. In this paper, we propose to integrate both approaches into a unified framework and design an unsupervised linear feature selective projection (FSP) for feature extraction with low-rank embedding and dual Laplacian regularization, with the aim to exploit the intrinsic relationship among data and suppress the impact of noise. Specifically, a projection matrix with an l2,1-norm regularization is introduced to project original high dimensional data points into a new subspace with lower dimension, where the l2,1-norm regularization can endow the projection with good interpretability. We deploy a coefficient matrix with low rank constraint to reconstruct the data points and the l2,1-norm is imposed to regularize the data reconstruction errors in the low-dimensional subspace and make FSP robust to noise. Furthermore, a dual graph Laplacian regularization term is imposed on the low dimensional data and data reconstruction matrix for preserving the local manifold geometrical structure of data. Finally, an alternatively iterative algorithm is carefully designed for solving the proposed optimization model. Theoretical convergence and computational complexity analysis of the algorithm are also provided. Comprehensive experiments on various benchmark datasets have been carried out to evaluate the performance of the proposed FSP. As indicated, our algorithm significantly outperforms other state-of-the-art methods for feature extraction.

Multiple kernel clustering (MKC) has been intensively studied during the last few decades. Even though they demonstrate promising clustering performance in various applications, existing MKC algorithms do not sufficiently consider the intrinsic neighborhood structure among base kernels, which could adversely affect the clustering performance. In this paper, we propose a simple yet effective neighbor-kernel-based MKC algorithm to address this issue. Specifically, we first define a neighbor kernel, which can be utilized to preserve the block diagonal structure and strengthen the robustness against noise and outliers among base kernels. After that, we linearly combine these base neighbor kernels to extract a consensus affinity matrix through an exact-rank-constrained subspace segmentation. The naturally possessed block diagonal structure of neighbor kernels better serves the subsequent subspace segmentation, and in turn, the extracted shared structure is further refined through subspace segmentation based on the combined neighbor kernels. In this manner, the above two learning processes can be seamlessly coupled and negotiate with each other to achieve better clustering. Furthermore, we carefully design an efficient iterative optimization algorithm with proven convergence to address the resultant optimization problem. As a by-product, we reveal an interesting insight into the exact-rank constraint in ridge regression by careful theoretical analysis: it back-projects the solution of the unconstrained counterpart to its principal components. Comprehensive experiments have been conducted on several benchmark data sets, and the results demonstrate the effectiveness of the proposed algorithm.

Incomplete multi-view clustering (IMVC) optimally fuses multiple pre-specified incomplete views to improve clustering performance. Among various excellent solutions, the recently proposed multiple kernel k-means with incomplete kernels (MKKM-IK) forms a benchmark, which redefines IMVC as a joint optimization problem where the clustering and kernel matrix imputation tasks are alternately performed until convergence. Though demonstrating promising performance in various applications, we observe that the manner of kernel matrix imputation in MKKM-IK would incur intensive computational and storage complexities, overcomplicated optimization and limitedly improved clustering performance. In this paper, we propose an Efficient and Effective Incomplete Multi-view Clustering (EE-IMVC) algorithm to address these issues. Instead of completing the incomplete kernel matrices, EE-IMVC proposes to impute each incomplete base matrix generated by incomplete views with a learned consensus clustering matrix. We carefully develop a three-step iterative algorithm to solve the resultant optimization problem with linear computational complexity and theoretically prove its convergence. Further, we conduct comprehensive experiments to study the proposed EE-IMVC in terms of clustering accuracy, running time, evolution of the learned consensus clustering matrix and the convergence. As indicated, our algorithm significantly and consistently outperforms some state-of-the-art algorithms with much less running time and memory.

Multi-view unsupervised feature selection (MV-UFS) aims to select a feature subset from multi-view data without using the labels of samples. However, we observe that existing MV-UFS algorithms do not well consider the local structure of cross views and the diversity of different views, which could adversely affect the performance of subsequent learning tasks. In this paper, we propose a cross-view local structure preserved diversity and consensus semantic learning model for MV-UFS, termed CRV-DCL briefly, to address these issues. Specifically, we project each view of data into a common semantic label space which is composed of a consensus part and a diversity part, with the aim to capture both the common information and distinguishing knowledge across different views. Further, an inter-view similarity graph between each pairwise view and an intra-view similarity graph of each view are respectively constructed to preserve the local structure of data in different views and different samples in the same view. An l2,1-norm constraint is imposed on the feature projection matrix to select discriminative features. We carefully design an efficient algorithm with convergence guarantee to solve the resultant optimization problem. Extensive experimental study is conducted on six publicly real multi-view datasets and the experimental results well demonstrate the effectiveness of CRV-DCL.

Efficient detection of outliers from massive data with a high outlier ratio is challenging but not explicitly discussed yet. In such a case, existing methods either suffer from poor robustness or require expensive computations. This paper proposes a Low-rank based Efficient Outlier Detection (LEOD) framework to achieve favorable robustness against high outlier ratios with much cheaper computations. Specifically, it is worth highlighting the following aspects of LEOD: (1) Our framework exploits the low-rank structure embedded in the similarity matrix and considers inliers/outliers equally based on this low-rank structure, which facilitates us to encourage satisfying robustness with low computational cost later; (2) A novel re-weighting algorithm is derived as a new general solution to the constrained eigenvalue problem, which is a major bottleneck for the optimization process. Instead of the high space and time complexity (O((2n)2)/O((2n)3)) required by the classic solution, our algorithm enjoys O(n) space complexity and a faster optimization speed in the experiments; (3) A new alternative formulation is proposed for further acceleration of the solution process, where a cheap closed-form solution can be obtained. Experiments show that LEOD achieves strong robustness under an outlier ratio from 20% to 60%, while it is at most 100 times more memory efficient and 1000 times faster than its previous counterpart that attains comparable performance. The codes of LEOD are publicly available at https://github.com/demonzyj56/LEOD.

Defocus blur detection aims to detect out-of-focus regions from an image. Although attracting more and more attention due to its widespread applications, defocus blur detection still confronts several challenges such as the interference of background clutter, sensitivity to scales and missing boundary details of defocus blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We firstly utilize a fully convolutional network to extract multi-scale deep features. The features from bottom layers are able to capture rich low-level features for details preservation, while the features from top layers can characterize the semantic information to locate blur regions. These features from different layers are fused as shallow features and semantic features, respectively. After that, the fused shallow features are propagated to top layers for refining the fine details of detected defocus blur regions, and the fused semantic features are propagated to bottom layers to assist in better locating the defocus regions. The feature fusing and refining are carried out in a recurrent manner. Also, we finally fuse the output of each layer at the last recurrent step to obtain the final defocus blur map by considering the sensitivity to scales of the defocus degree. Experiments on two commonly used defocus blur detection benchmark datasets are conducted to demonstrate the superority of DeFusionNet when compared with other 10 competitors. Code and more results can be found at: http://tangchang.net.

This paper proposes a novel deep saliency detection network by recurrently aggregating and refining features in a cross-level and spatial attention-aware manner. In this way, the features integrated from multiple layers can be used to refine layer-wise features step by step and the complementary information in different layers can be fully captured for detecting salient objects with different scales, i.e., the features integrated from low-level layers can serve to refine the details of detected salient objects while the features integrated from high-level layers with semantic information can benefit the locating of salient objects. In addition, by considering that only partial regions of an image are salient, we embed a spatial attention-aware module to suppress the non-salient regions and highlight salient objects. Finally, different saliency detection results from different layers are fused to generate the final saliency map. Experimental results on five benchmark datasets demonstrate that our proposed method outperforms other 14 state-of-the-art competitors.

Existing deep neural networks mainly focus on learning transformation invariant features. However, it is the equivariant features that are more adequate for general purpose tasks. Unfortunately, few work has been devoted to learning equivariant features. To fill this gap, in this paper, we propose an affine equivariant autoencoder to learn features that are equivariant to the affine transformation in an unsupervised manner. The objective consists of the self-reconstruction of the original example and affine transformed example, and the approximation of the affine transformation function, where the reconstruction makes the encoder a valid feature extractor and the approximation encourages the equivariance. Extensive experiments are conducted to validate the equivariance and discriminative ability of the features learned by our affine equivariant autoencoder.

Multi-view clustering (MVC) optimally integrates complementary information from different views to improve clustering performance. Although demonstrating promising performance in many applications, we observe that most of existing methods directly combine multiple views to learn an optimal similarity for clustering. These methods would cause intensive computational complexity and over-complicated optimization. In this paper, we theoretically uncover the connection between existing k-means clustering and the alignment between base partitions and consensus partition. Based on this observation, we propose a simple but effective multi-view algorithm termed {Multi-view Clustering via Late Fusion Alignment Maximization (MVC-LFA)}. In specific, MVC-LFA proposes to maximally align the consensus partition with the weighted base partitions. Such a criterion is beneficial to significantly reduce the computational complexity and simplify the optimization procedure. Furthermore, we design a three-step iterative algorithm to solve the new resultant optimization problem with theoretically guaranteed convergence. Extensive experiments on five multi-view benchmark datasets demonstrate the effectiveness and efficiency of the proposed MVC-LFA.

Incomplete multi-view clustering has attracted various attentions from diverse fields. Most existing methods factorize data to learn a unified representation linearly. Their performance may degrade when the relations between the unified representation and data of different views are nonlinear. Moreover, they need post-processing on the unified representations to extract the clustering indicators, which separates the consensus learning and subsequent clustering. To address these issues, in this paper, we propose a Simultaneous Representation Learning and Clustering (SRLC) method. Concretely, SRLC constructs similarity matrices to measure the relations between pair of instances, and learns low-dimensional representations of present instances on each view and a common probability label matrix simultaneously. Thus, the nonlinear information can be reflected by these representations and the clustering results can obtained from label matrix directly. An efficient iterative algorithm with guaranteed convergence is presented for optimization. Experiments on several datasets demonstrate the advantages of the proposed approach.

Video anomaly detection is a valuable but challenging task, especially in the field of surveillance videos for public safety. Almost all existing methods tackle the problem under the supervised setting and only a few attempts are conducted on the unsupervised learning. To avoid the cost of labeling training videos, this paper proposes to discriminate anomaly by a novel two-stage framework in a fully unsupervised manner. Unlike previous unsupervised approaches using local change detection to discover abnormality, our method enjoys the global information from video context by considering the pair-wise similarity of all video events. In this way, our method formulates video anomaly detection as an extension of unsupervised one-class learning, which has not been explored in the literature of video anomaly detection. Specifically, our method consists of two stages: The first stage of our kernel-based method, named Low-rank based Unsupervised One-class Learning with Ridge Regression (LR-UOCL-RR), reformulates the optimization goal of UOCL with ridge regression to avoid expensive computation, which enables our method to handle massive unlabeled data from videos. In the second stage, the estimated normal video events from the first stage are fed into the one-class support vector machine to refine the profile around normal events and enhance the performance. The experimental results conducted on two challenging video benchmarks indicate that our method is considerably superior, up to 15:7% AUC gain, to the state-of-the-art methods in the unsupervised anomaly detection task and even better than several supervised approaches.

Despite the wide success of deep neural networks (DNN), little progress has been made on end-to-end unsupervised outlier detection (UOD) from high dimensional data like raw images. In this paper, we propose a framework named E^3Outlier, which can perform UOD in a both effective and end-to-end manner: First, instead of the commonly-used autoencoders in previous end-to-end UOD methods, E^3Outlier for the first time leverages a discriminative DNN for better representation learning, by using surrogate supervision to create multiple pseudo classes from original unlabelled data. Next, unlike classic UOD that utilizes data characteristics like density or proximity, we exploit a novel property named inlier priority to enable end-to-end UOD by discriminative DNN. We demonstrate theoretically and empirically that the intrinsic class imbalance of inliers/outliers will make the network prioritize minimizing inliers' loss when inliers/outliers are indiscriminately fed into the network for training, which enables us to differentiate outliers directly from DNN's outputs. Finally, based on inlier priority, we propose the negative entropy based score as a simple and effective outlierness measure. Extensive evaluations show that E^3Outlier significantly advances UOD performance by up to 30% AUROC against state-of-the-art counterparts, especially on relatively difficult benchmarks.

The k-means clustering is arguably the most popular clustering technique, which has been applied to a wide range of applications. Lloyd’s algorithm is the most popular algorithm for the k-means problem due to its simplicity, geometric intuition and effectiveness. However, in a naive implementation of Lloyd’s algorithm, we need to compute the Euclidean distances between all data points and all cluster centers in each iteration. This prevents the algorithm from being scalable to large datasets and becomes the main bottleneck. To overcome the problem, this paper proposes two scalable k-means algorithms, Scalable Lloyd’s k-means and Scalable Mini-Batch k-means. They are distributed extensions of Lloyd’s algorithm and the mini-batch k-means, respectively. The two algorithms are all use the data-parallel technique to scale beyond computational and memory limits of a single machine. Meanwhile, they are all based on the parameter server abstraction that facilitates the data-parallel computation. The first algorithm can find better quality of solutions, while the second one converges to a modest solution faster. They both have good scalability and totally do in-memory computation. In addition, we propose a new aggregation method for Scalable Mini-Batch k-means. Extensive experiments conducted on four large-scale datasets show that our proposed algorithms have good convergence performance and achieve almost ideal speedup.

Incomplete multi-view clustering optimally integrates a group of pre-specified incomplete views to improve clustering performance. Among various excellent solutions, multiple kernel $k$k-means with incomplete kernels forms a benchmark, which redefines the incomplete multi-view clustering as a joint optimization problem where the imputation and clustering are alternatively performed until convergence. However, the comparatively intensive computational and storage complexities preclude it from practical applications. To address these issues, we propose Late Fusion Incomplete Multi-view Clustering (LF-IMVC) which effectively and efficiently integrates the incomplete clustering matrices generated by incomplete views. Specifically, our algorithm jointly learns a consensus clustering matrix, imputes each incomplete base matrix, and optimizes the corresponding permutation matrices. We develop a three-step iterative algorithm to solve the resultant optimization problem with linear computational complexity and theoretically prove its convergence. Further, we conduct comprehensive experiments to study the proposed LF-IMVC in terms of clustering accuracy, running time, advantages of late fusion multi-view clustering, evolution of the learned consensus clustering matrix, parameter sensitivity and convergence. As indicated, our algorithm significantly and consistently outperforms some state-of-the-art algorithms with much less running time and memory.

Recently, network lasso has dawn much attention due to its remarkable performance on simultaneous clustering and optimization. However, it usually suffers from the imperfect data (noise, missing values, etc.), and yields sub-optimal solutions. The reason is that it finds the similar instances according to their features directly, which is usually impacted by the imperfect data, and thus returns sub-optimal results. In this paper, we propose triangle lasso to avoid its disadvantage for graph datasets. In a graph dataset, each instance is represented by a vertex. If two instances have many common adjacent vertices, they tend to become similar. Although some instances are profiled by the imperfect data, it is still able to find the similar counterparts. Furthermore, we develop an efficient algorithm based on Alternating Direction Method of Multipliers (ADMM) to obtain a moderately accurate solution. In addition, we present a dual method to obtain the accurate solution with the low additional time consumption. We demonstrate through extensive numerical experiments that triangle lasso is robust to the imperfect data. It usually yields a better performance than the state-of-the-art method when performing data analysis tasks in practical scenarios.

Multilabel image annotation attracts a lot of research interest due to its practicability in multimedia and computer vision fields, while the need for a large amount of labeled training data to achieve promising performance makes it a challenging task. Fortunately, unlabeled and relevant data are widely available and these data can be used to serve the annotation task. To this end, we propose a novel adaptive hypergraph learning (AHL) method for multilabel image annotation in a semisupervised way, in which both the limited labeled data and abundant unlabeled data are utilized to facilitate the annotation performance. In detail, we seek a multilabel propagation scheme by learning a hypergraph which is used to preserve the local geometric structures of data in a high-order manner. Meanwhile, a feature projection is integrated into AHL to obtain a latent feature space where unlabeled instances can be effectively and robustly assigned with multiple labels. Experiments on six widely used image datasets are conducted to evaluate our model and the results demonstrate that the proposed AHL outperforms other state-of-the-art semisupervised methods.

With the ability to exploit the internal structure of data, graph-based models have received a lot of attention and have achieved great success in multiview subspace clustering for multimedia data. Most of the existing methods individually construct an affinity graph for each single view and fuse the result obtained from each single graph. However, the common representation shared by different views and the complementary diversity across these views are not efficiently exploited. In addition, noise and outliers are often mixed in original data, which adversely degenerate the clustering performance of many existing methods. In this paper, we propose addressing these issues by learning a joint affinity graph for multiview subspace clustering based on a low-rank representation with diversity regularization and a rank constraint. Specifically, a low-rank representation model is employed to learn a shared sample representation coefficient matrix to generate the affinity graph. At the same time, we use diversity regularization to learn the optimal weights for each view, which can suppress the redundancy and enhance the diversity among different feature views. In addition, the cluster number is used to promote affinity graph learning by using a rank constraint. The final clustering result is obtained by using normalized cuts on the learned affinity graph. An efficient algorithm based on an augmented Lagrangian multiplier with alternating direction minimization is carefully designed to solve the resulting optimization problem. Extensive experiments on various real-world datasets are conducted, and the results demonstrate well the effectiveness of the proposed algorithm.

With the advent of multi-view data, multi-view learning (MVL) has become an important research direction in machine learning. It is usually expected that multi-view algorithms can obtain better performance than that of merely using a single view. However, previous researches have pointed out that sometimes the utilization of multiple views may even deteriorate the performance. This will be a stumbling block for the practical use of MVL in real applications, especially for tasks requiring high dependability. Thus, it is eager to design reliable multi-view approaches, such that their performance is never degenerated by exploiting multiple views.This issue is vital but rarely studied. In this paper, we focus on clustering and propose the Reliable Multi-View Clustering (RMVC) method. Based on several candidate multi-view clusterings, RMVC maximizes the worst-case performance gain against the best single view clustering, which is equivalently expressed as no label information available. Specifically, employing the squared χ2 distance for clustering comparison makes the formulation of RMVC easy to solve, and an efficient strategy is proposed for optimization. Theoretically, it can be proved that the performance of RMVC will never be significantly decreased under some assumption. Experimental results on a number of data sets demonstrate that the proposed method can effectively improve the reliability of multi-view clustering.

A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities. The ranking loss consists of intra-modality and cross-modality triplet losses, and it reduces both the intra-modality and cross-modality feature variations. Furthermore, the correlations between RGB and depth data are embedded in the c-ConvNet, and can be retrieved by either of the modalities and contribute to the recognition in the case even only one of the modalities is available. The proposed method was extensively evaluated on two large RGB-D action recognition datasets, ChaLearn LAP IsoGD and NTU RGB+D datasets, and one small dataset, SYSU 3D HOI, and achieved state-of-the-art results.

Determining the number of clusters is important but challenging, especially for data of high dimension. In this paper, we propose Deep Embedding Determination (DED), a method that can solve jointly for the unknown number of clusters and feature extraction. DED first combines the virtues of the convolutional autoencoder and the t-SNE technique to extract low dimensional embedded features. Then it determines the number of clusters using an improved density-based clustering algorithm. Our experimental evaluation on image datasets shows significant improvement over state-of-the-art methods and robustness with respect to hyperparameter settings.

For real-world applications, data are often associated with multiple labels and represented with multiple views. Most existing multi-label learning methods do not sufficiently consider the complementary information among multiple views, leading to unsatisfying performance. To address this issue, we propose a novel approach for multi-view multi-label learning based on matrix factorization to exploit complementarity among different views. Specifically, under the assumption that there exists a common representation across different views, the uncovered latent patterns are enforced to be aligned across different views in kernel spaces. In this way, the latent semantic patterns underlying in data could be well uncovered and this enhances the reasonability of the common representation of multiple views. As a result, the consensus multi-view representation is obtained which encodes the complementarity and consistence of different views in latent semantic space. We provide theoretical guarantee for the strict convexity for our method by properly setting parameters. Empirical evidence shows the clear advantages of our method over the state-of-the-art ones.

It is challenging to perform k-means clustering on a large scale dataset efficiently. One of the reasons is that k-means needs to scan a batch of training data to update the cluster centers at every iteration, which is time-consuming. In the paper, we propose a variance reduced k-mean VRKM, which outperforms the state-of-the-art method, and obtain 4× speedup for large-scale clustering. The source code is available on https://github.com/YaweiZhao/VRKM_sofia-ml.

Deep Embedded Clustering (DEC) surpasses traditional clustering algorithms by jointly performing feature learning and cluster assignment. Although a lot of variants have emerged, they all ignore a crucial ingredient, \emph{data augmentation}, which has been widely employed in supervised deep learning models to improve the generalization. To fill this gap, in this paper, we propose the framework of Deep Embedded Clustering with Data Augmentation (DEC-DA). Specifically, we first train an autoencoder with the augmented data to construct the initial feature space. Then we constrain the embedded features with a clustering loss to further learn clustering-oriented features. The clustering loss is composed of the target (pseudo label) and the actual output of the feature learning model, where the target is computed by using clean (non-augmented) data, and the output by augmented data. This is analogous to supervised training with data augmentation and expected to facilitate unsupervised clustering too. Finally, we instantiate five DEC-DA based algorithms. Extensive experiments validate that incorporating data augmentation can improve the clustering performance by a large margin. Our DEC-DA algorithms become the new state of the art on various datasets.

This work presents a simple yet effective model for multi-view metric learning, which aims to improve the classification of data with multiple views, e.g., multiple modalities or multiple types of features. The intrinsic correlation, different views describing same set of instances, makes it possible and necessary to jointly learn multiple metrics of different views, accordingly, we propose a multi-view metric learning method based on Fisher discriminant analysis (FDA) and Hilbert-Schmidt Independence Criteria (HSIC), termed as Fisher-HSIC Multi-View Metric Learning (FISH-MML). In our approach, the class separability is enforced in the spirit of FDA within each single view, while the consistence among different views is enhanced based on HSIC. Accordingly, both intra-view class separability and inter-view correlation are well addressed in a unified framework. The learned metrics can improve multi-view classification, and experimental results on real-world datasets demonstrate the effectiveness of the proposed method.

The recently proposed multiple kernel k-means with incomplete kernels (MKKM-IK) optimally integrates a group of pre-specified incomplete kernel matrices to improve clustering performance. Though it demonstrates promising performance in various applications, we observe that it does not \emph{sufficiently consider the local structure among data and indiscriminately forces all pairwise sample similarity to equally align with their ideal similarity values}. This could make the incomplete kernels less effectively imputed, and in turn adversely affect the clustering performance. In this paper, we propose a novel localized incomplete multiple kernel k-means (LI-MKKM) algorithm to address this issue. Different from existing MKKM-IK, LI-MKKM only requires the similarity of a sample to its k-nearest neighbors to align with their ideal similarity values. This helps the clustering algorithm to focus on closer sample pairs that shall stay together and avoids involving unreliable similarity evaluation for farther sample pairs. We carefully design a three-step iterative algorithm to solve the resultant optimization problem and theoretically prove its convergence. Comprehensive experiments on eight benchmark datasets demonstrate that our algorithm significantly outperforms the state-of-the-art comparable algorithms proposed in the recent literature, verifying the advantage of considering local structure.

Recent research indicates the critical importance of preserving local geometric structure of data in unsupervised feature selection (UFS), and the well studied graph Laplacian is usually deployed to capture this property. By using a squared l 2 -norm, we observe that conventional graph Laplacian is sensitive to noisy data, leading to unsatisfying data processing performance. To address this issue, we propose a unified UFS framework via feature self-representation and robust graph regularization , with the aim at reducing the sensitivity to outliers from the following two aspects: i) an l 2, 1 -norm is used to characterize the feature representation residual matrix; and ii) an l 1 -norm based graph Laplacian regularization term is adopted to preserve the local geometric structure of data. By this way, the proposed framework is able to reduce the effect of noisy data on feature selection. Furthermore, the proposed l 1 -norm based graph Laplacian is readily extendible, which can be easily integrated into other UFS methods and machine learning tasks with local geometrical structure of data being preserved. As demonstrated on ten challenging benchmark data sets, our algorithm significantly and consistently outperforms state-of-the-art UFS methods in the literature, suggesting the effectiveness of the proposed UFS framework.

Despite the increasing popularity and successful examples of crowdsourcing, it is stripped of aureole when collective efforts are derailed or severely hindered by elaborate sabotage. A service exchange dilemma arises when there is non-cooperation among self-interested users, and zero social welfare is obtained at myopic equilibrium. Traditional rating protocols are not effective to overcome the inefficiency of the socially undesirable equilibrium due to specific features of crowdsourcing: a large number of anonymous users having asymmetric service requirements, different service capabilities, and dynamically joining/leaving a crowdsourcing platform with imperfect monitoring. In this paper, we develop the first game-theoretic design of the two-sided rating protocol to stimulate cooperation among self-interested users, which consists of a recommended strategy and a rating update rule. The recommended strategy recommends a desirable behavior from three predefined plans according to intrinsic parameters, while the rating update rule involves the update of ratings of both users, and uses differential punishments that punish users with different ratings differently. By quantifying necessary and sufficient conditions for a sustainable social norm, we formulate the problem of designing an optimal two-sided rating protocol that maximizes the social welfare among all sustainable protocols, provide design guidelines for optimal two-sided rating protocols and a low-complexity algorithm to select optimal design parameters in an alternate manner. Finally, evaluation results show the validity and effectiveness of our protocol designed for service exchange dilemma in crowdsourcing.

Multiple kernel clustering (MKC) algorithms optimally combine a group of pre-specified base kernels to improve clustering performance. However, existing MKC algorithms cannot efficiently address the situation where some rows and columns of base kernels are absent. This paper proposes a simple while effective algorithm to address this issue. Different from existing approaches where incomplete kernels are firstly imputed and a standard MKC algorithm is applied to the imputed kernels, our algorithm integrates imputation and clustering into a unified learning procedure. Specifically, we perform multiple kernel clustering directly with the presence of incomplete kernels, which are treated as auxiliary variables to be jointly optimized. Our algorithm does not require that there be at least one complete base kernel over all the samples. Also, it adaptively imputes incomplete kernels and combines them to best serve clustering. A three-step iterative algorithm with proved convergence is designed to solve the resultant optimization problem. Extensive experiments are conducted on four benchmark data sets to compare the proposed algorithm with existing imputation-based methods. Our algorithm consistently achieves superior performance and the improvement becomes more significant with increasing missing ratio, verifying the effectiveness and advantages of the proposed joint imputation and clustering.

Multiple kernel $k$-means (MKKM) aims to improve clustering performance by learning an optimal kernel, which is usually assumed to be a linear combination of a group of pre-specified base kernels. However, we observe that this assumption could: i) cause limited kernel representation capability; and ii) not sufficiently consider the negotiation between the process of learning the optimal kernel and that of clustering, leading to unsatisfying clustering performance. To address these issues, we propose an optimal neighborhood kernel clustering (ONKC) algorithm to enhance the representability of the optimal kernel and strengthen the negotiation between kernel learning and clustering. We theoretically justify this ONKC by revealing its connection with existing MKKM algorithms. Furthermore, this justification shows that existing MKKM algorithms can be viewed as a special case of our approach and indicates the extendability of the proposed ONKC for designing better clustering algorithms. An efficient algorithm with proved convergence is designed to solve the resultant optimization problem. Extensive experiments have been conducted to evaluate the clustering performance of the proposed algorithm. As demonstrated, our algorithm significantly outperforms the state-of-the-art ones in the literature, verifying the effectiveness and advantages of ONKC.

Compressive spectral clustering (CSC) efficiently leverages graph filter and random sampling techniques to speed up clustering process. However, we find that CSC algorithm suffers from two main problems: i) The direct use of the dichotomy and eigencount techniques for estimating laplacian matrix’s k-th eigenvalue is expensive. ii) The computation of polynomial approximation repeats in each iteration for every cluster in the interpolation process, which occupies most of the computation time of CSC. To address these problems, we propose a new approach called FCSC for fast compressive spectral clustering. FCSC addresses the first problem by assuming that the eigenvalues approximately satisfy local uniform distribution, and addresses the second problem by recalculating the pairwise similarity between nodes with low-dimensional representation to reconstruct denoised laplacian matrix. The time complexity of reconstruction is linear with the number of non-zeros in laplacian matrix. As experimentally demonstrated on artificial and real-world datasets, our approach significantly reduces the computation time while preserving high clustering accuracy comparable to previous designs, verifying the effectiveness of FCSC.

Deep clustering learns deep feature representations that favor clustering task using neural networks. Some pioneering work proposes to simultaneously learn embedded features and perform clustering by explicitly defining a clustering oriented loss. Though promising performance has been demonstrated in various applications, we observe that a vital ingredient has been overlooked by these work that the defined clustering loss may corrupt feature space, which leads to non-representative meaningless features and this in turn hurts clustering performance. To address this issue, in this paper, we propose the Improved Deep Embedded Clustering (IDEC) algorithm to take care of data structure preservation. Specifically, we manipulate feature space to scatter data points using a clustering loss as guidance. To constrain the manipulation and maintain the local structure of data generating distribution, an under-complete autoencoder is applied. By integrating the clustering loss and autoencoder's reconstruction loss, IDEC can jointly optimize cluster labels assignment and learn features that are suitable for clustering with local structure preservation. The resultant optimization problem can be effectively solved by mini-batch stochastic gradient descent and backpropagation. Experiments on image and text datasets empirically validate the importance of local structure preservation and the effectiveness of our algorithm.

Multiple kernel clustering (MKC) algorithms have been successfully applied into various applications. However, these successes are largely dependent on the quality of pre-defined base kernels, which cannot be guaranteed in practical applications. This may adversely affect the clustering performance. To address this issue, we propose a simple while effective framework to adaptively improve the quality of these base kernels. Under our framework, we instantiate three MKC algorithms based on the widely used multiple kernel $k$-means clustering (MKKM), MKKM with matrix-induced regularization (MKKM-MR) and co-regularized multi-view spectral clustering (CRSC). After that, we design the corresponding algorithms with proved convergence to solve the resultant optimization problems. To the best of our knowledge, our framework fills the gap between kernel adaption and clustering procedure for the first time in the literature and is readily extendable. Extensive experimental research has been conducted on 7 MKC benchmarks. As is shown, our algorithms consistently and significantly improve the performance of the base MKC algorithms, indicating the effectiveness of the proposed framework. Meanwhile, our framework shows better performance than compared ones with imperfect kernels.

Multiple kernel clustering (MKC) algorithms have been extensively studied and applied to various applications. Although they demonstrate great success in both the theoretical aspects and applications, existing MKC algorithms cannot be applied to large-scale clustering tasks due to: i) the heavy computational cost to calculate the base kernels; and ii) insufficient memory to load the kernel matrices. In this paper, we propose an approximate algorithm to overcome these issues, and to make it be applicable to large-scale applications. Specifically, our algorithm trains a deep neural network to regress the indicating matrix generated by MKC algorithms on a small subset, and then obtains the approximate indicating matrix of the whole data set using the trained network, and finally performs the $k$-means on the output of our network. By mapping features into indicating matrix directly, our algorithm avoids computing the full kernel matrices, which dramatically decreases the memory requirement. Extensive experiments show that our algorithm consumes less time than most comparatively similar algorithms, while it achieves comparable performance with MKC algorithms.

Multiple kernel k-means (MKKM) clustering aims to optimally combine a group of pre-specified kernels to improve clustering performance. However, we observe that existing MKKM algorithms do not sufficiently consider the correlation among these kernels. This could result in selecting mutually redundant kernels and affect the diversity of information sources utilized for clustering, which finally hurts the clustering performance. To address this issue, this paper proposes an MKKM clustering with a novel, effective matrix-induced regularization to reduce such redundancy and enhance the diversity of the selected kernels. We theoretically justify this matrix-induced regularization by revealing its connection with the commonly used kernel alignment criterion. Furthermore, this justification shows that maximizing the kernel alignment for clustering can be viewed as a special case of our approach and indicates the extendability of the proposed matrix-induced regularization for designing better clustering algorithms. As experimentally demonstrated on five challenging MKL benchmark data sets, our algorithm significantly improves existing MKKM and consistently outperforms the state-of-the-art ones in the literature, verifying the effectiveness and advantages of incorporating the proposed matrix-induced regularization.