Robust signal enhancement under non-stationary and low SNR conditions remains challenging, as methods based on the short-time Fourier transform (STFT) with fixed resolution struggle to represent complex and time–frequency structures. While leveraging the fractional domain as an auxiliary view offers flexibility in modeling time-frequency structures, existing methods typically adopt fixed transform orders and overlook alignment between views, hindering effective integration of complementary representations and leaving frequency domain misalignment unresolved. Therefore, we propose FracFusion, a novel framework that integrates a learnable short-time fractional Fourier Transform (STFrFT) module to generate dynamic auxiliary views, combined with two stage alignment-aware fusion modules: Pearson Channel Fusion for correlation-guided consistency and Efficient Align Fusion for fine-grained, frequency aligned interaction. Experiments on speech and electromagnetic (EM) datasets show that FracFusion consistently outperforms state-of-the-art baselines across diverse noise levels and signal types, demonstrating robust adaptability across domains.

In multi-view classification tasks (MVC), each view provides an unique perspective on the data, offering complementary information that can improve classification performance when properly integrated. However, traditional methods typically adopt a uniform processing strategy for all views before fusion, overlooking the fact that different views may require different treatments due to variations in their quality and informativeness. To address this limitation, we propose a novel framework called Uncertainty-Guided View-Strength-Aware Feature Utilization (UVF) for multi-view classification. Our approach introduces a view uncertainty estimation module to quantify the discriminative strength of each view. Based on this estimation, a Differentiated Feature Selector (DFS) adaptively selects features, retaining informative dimensions in weak views while preserving original features in strong views. Furthermore, we employ an uncertainty-guided fusion strategy that assigns dynamic weights to each view's contribution based on its uncertainty score, enhancing the robustness and reliability of the final decision. Experimental results on benchmark datasets demonstrate that our method significantly outperforms conventional approaches, achieving better classification accuracy and interpretability through strength-aware feature processing and fusion.

Modern multi-view clustering (MVC) is dominated by two paradigms: multi-view fusion and pseudo-label-guided learning. Pseudo-labeling methods can suffer from confirmation bias; their reliance on a fixed-granularity supervision from an initial clustering can cause learned embeddings to drift from the data's true structure and lose discriminative power. Conversely, fusion methods excel at integrating information but often struggle to robustly differentiate between high-quality and noisy views, which can obscure final cluster boundaries and degrade performance. To address these complementary challenges, we propose GAPS (Granularity-Aware Pseudo Supervision), a novel MVC framework. GAPS introduces a granularity-aware supervision mechanism that generates a full hierarchy of pseudo-labels, enabling the selection of a supervision level that best aligns with the data's intrinsic multi-scale structure. Furthermore, to ensure a high-quality supervisory signal, it incorporates a reliability-aware view selection strategy using a novel Separation-Compactness Index (SCI) to identify and leverage the most informative view for pseudo-label generation. This dual approach ensures the supervisory signal is both structurally adaptive and derived from the most reliable source, leading to highly effective final representations. Extensive experiments on synthetic and real-world datasets demonstrate the effectiveness and superiority of GAPS over other competitors.

With the growing demand for decentralized collaborative analysis of privacy-sensitive data, federated multi-view clustering (FMVC) has attracted widespread attention due to its ability to balance privacy protection and collaborative modeling. However, current methods still face the following challenges: (1) Clients need to frequently upload high-dimensional data such as model parameters or graph structures, resulting in high communication costs; (2) The structured data uploaded often contains semantic features and has a high risk of being inverted; (3) The server usually merges the data from all clients with the fixed fusion rule, which may result in a suboptimized clustering result when there exist low-quality clients. To address the issues, we propose a new trusted federated multi-view clustering framework (EvoFMVC) that introduces three key innovations: First, lightweight trusted evidence serves as a compact communication medium, significantly reducing overhead compared to conventional model parameters or graph structures. Second, trusted evidences express clustering results in the form of probability distribution, which avoids the risk of structured information being easily inverted. Lastly, we formalize the server-side aggregation process as a neural architecture search (NAS) task where the server flexibly uses different fusion operators to filter and fuse necessary views through evolutionary algorithms, which significantly improves the fusion effect and model performance. Experimental results on multiple datasets show that our method is superior to existing FMVC methods in terms of clustering accuracy and communication efficiency.

Clustering on high-dimensional and low sample size (HDLSS) data remains a critical, persistent challenge where extreme sparsity and noise confound cluster analysis. This creates a dilemma: spectral methods fail as distance metrics degrade, while deep clustering tends to over-fit scarce data. To break this dilemma, a Self-Enhanced Density Clustering (SEDC) framework that integrates the cluster structure discovery and embedding representation learning into an iterative enhancement process is proposed in this paper. Specifically, SEDC uses adaptive density-derived centroids to parameterize probabilistic soft labels, which in turn supervise a lightweight multilayer perceptron (MLP) to learn the low-dimensional embedding from data. The resulting embedding provides a refined metric space for further generating superior labels in the subsequent interaction process. This feedback forms a mutual reinforcement that progressively enhances the discrimination of embedding while rigorously mitigating over-fitting. Extensive experiments on 43 challenging HDLSS datasets demonstrate state-of-the-art performance, substantially outperforming popular clustering methods. This work delivers a principled and promising solution for robust data clustering in HDLSS situations.

Detecting and identifying complex association patterns between two variables is a fundamental task. This requires association measures that satisfy both generality (the ability to capture a wide range of association structures) and equitability (the absence of bias toward specific association types). Designing such measures is challenging due to the distributional uncertainty, structural diversity, and mixture of association types found in large datasets. Granular computing offers a promising direction, as local neighborhood structures naturally encode multi-scale association information. Inspired by this insight, we introduce the maximal neighborhood coefficient (MNC), an association measure based on $k$k-NN granulation. MNC captures a broad range of associations without empirical bias while retaining local structural details often missed by existing measures. Extending this idea, we develop a family of maximal neighborhood nonparametric exploration (MNNE) statistics that supply richer auxiliary information for characterizing associations. Together, MNC and MNNE form a data-driven exploration toolkit that offers strong empirical performance and a new perspective on mining complex association patterns.

Most existing robotic grasp detection methods can achieve high accuracy in one single domain, but due to the differences in data distribution and object categories among different datasets, the accuracies of these methods decrease significantly in other domains. To solve this problem, we propose a novel domain-invariant grasp detection network with scene prototypes and structure priors to extract robust grasping features. First, a universal prototype guidance strategy, which models the hidden domain scenes and obtains universal scene prototypes based on their similarities, is designed to distinguish foreground objects from background in different domains. The structure perception enhancement method based on structure priors is then constructed to carry out fine-grained modeling of foreground regions and capture more detailed local information. In addition, we also design repulsive constraint regularization to assist the training process to alleviate the issue of similar prior distribution in vector space. Extensive comparative experiments are conducted on four public datasets and the results show that the proposed method achieves significant improvements of detection accuracy under cross-dataset scenarios. As a plug-in module, it could improve the generalization of existing grasp detection approaches by a large margin. Real-world robotic grasping experiments are also deployed to verify its effectiveness.

Multi-modal classification (MMC) leverages effective fusion of information from diverse modalities to achieve superior classification performance. Existing fusion methods, however, rely on expert-designed architectures that demand substantial domain expertise and computational resources, with fixed topologies that offer limited structural flexibility across tasks and datasets. Although neural architecture search (NAS)-based fusion methods have been proposed to automatically discover high-performing architectures, these approaches are computationally expensive and predominantly rely on pairwise modality combinations, which fail to capture complex multi-variable correlations, limiting the architectures' expressiveness and flexibility. Consequently, there remains a lack of multi-modal fusion frameworks that can simultaneously achieve high efficiency and high accuracy. To break through these bottlenecks, we propose a multi-branch tree-based fusion neural architecture search framework (MBTF-NAS). For performance enhancement, MBTF-NAS employs a multi-branch tree-structured encoding strategy that enables dynamic and computationally efficient exploration of fusion topologies and substantially strengthens cross-modal interaction. A learnable model-level attention weighting mechanism further emphasizes informative modalities, improving the overall quality of multi-modal feature fusion. For efficiency improvement, MBTF-NAS leverages zero-cost proxy metrics for architecture evaluation, enabling rapid identification of high-potential candidates while dramatically reducing computational overhead. We conducted a comprehensive evaluation of MBTF-NAS on seven representative multi-modal benchmarks. The experimental results demonstrate that MBTF-NAS consistently outperforms state-of-the-art approaches, highlighting its effectiveness and generalizability.

As partial samples are often absent in certain views, incomplete multi-view clustering has become a challenging task. To tackle data with missing views, current methods either utilize the data similarity relations to recover missing samples or primarily consider the available information of existing samples, typically facing some inherent limitations. Firstly, traditional solutions cannot fully explore the potential information contained in missing samples due to their omission strategy, leading to sub-optimal graphs. Moreover, most methods mainly focus on data recovery from the view level, ignoring the differences among available/missing samples in various views. To this end, we propose a collaborative Similarity Fusion and Consistency Recovery (SFCR) method, which resolves the incomplete multi-view clustering problem by learning a unified similarity graph and recovering missing samples with consistent structures. Specifically, to learn a reliable graph compatible across views, a novel view-to-sample fusion model is designed to adaptively coalesce the view-wise similarities among available samples, not only preserving the complementarity and consistency among views but also properly balancing different samples. Furthermore, the missing samples are effectively recovered under the guidance of the fused similarity graph, so as to maintain the consistent structure of recovered data across views. In this way, the similarity learning and the missing data recovery benefit from each other in a collaborative reinforcement manner. Meanwhile, SFCR can directly obtain the final clustering labels without additional post-processing. Extensive experiments demonstrate the effectiveness and superiority of SFCR.

As a foundational clustering paradigm, Density Peak Clustering (DPC) partitions samples into clusters based on their density peaks, garnering widespread attention. However, traditional DPC methods usually focus on high-density regions, neglecting representative peaks in relatively low-density areas, particularly in datasets with varying densities and multiple peaks. Moreover, existing DPC variants struggle to identify clusters correctly in high-dimensional spaces due to the indistinct distance differences among samples and sparse data distributions. Additionally, existing methods typically adopt a one-step label assignment strategy, making them prone to cascading errors when initial misassignments occur. To address these challenges, we propose an Enhanced Density Peak Clustering (EDPC) method, which creatively incorporates multilayer perceptron (MLP)-based dimensionality reduction and a hierarchical label assignment strategy to significantly improve clustering performance in high-dimensional scenarios. Specifically, we introduce an effective selection condition that combines average densities and density-related distances to generate potential cluster centers, ensuring that peaks across different density regions are considered simultaneously. Furthermore, an MLP, guided by pseudo-labels from sub-clusters, is designed to learn low-dimensional embeddings for high-dimensional data, preserving data locality while enhancing clusterability. Extensive experiments demonstrate the effectiveness and superiority of EDPC against state-of-the-art DPC methods.

Multi-modal medical image fusion has demonstrated considerable promise in clinical diagnostics by enabling comprehensive pathological assessment through the integration of complementary information. However, most existing joint registration and fusion methods rely on simulated deformations to construct misaligned training data, which may limit their effectiveness in handling realistic misalignment scenarios. Furthermore, the inherent heterogeneity of multi-modal images creates substantial modality gaps that present significant technical challenges. To overcome these limitations, we introduce a single, end-toend framework for the simultaneous alignment and fusion of medical images in a mutually reinforcing manner. The core of our approach is a novel representation learning module that effectively decomposes inputs into modality-common and modality-specific features. Specifically, we propose a Decoupled Common and Specific Feature (DCSF) Module to extract shared representations for bridging the modality gap and capture modality-specific characteristics to incorporate complementary information. To tackle the modality-invariant feature alignment problem, we propose a Modality-Common Feature Alignment (MCFA) Module, which constructs cross-modal feature mappings based on disparate imaging physics and simultaneously maintains spatial structural coherence and spectral feature consistency. Extensive experiments demonstrate that our MCSAF achieves promising performance on three benchmark multi-modal medical datasets.

Multi-view classification based on the Dempster-Shafer theory is widely recognized for its reliability in safety-critical domains with multi-view data. However, the adoption of a late fusion strategy constrains information interaction among views, thereby leading to suboptimal utilization of multi-view data. A recent advancement addressing this limitation involves generating a pseudo view by concatenating individual views. Yet, the efficacy of this pseudo view may diminish when incorporating underperforming views like noisy views. Additionally, the integration of a pseudo view exacerbates the issue of imbalanced multi-view learning, as it contains a disproportionate amount of information compared to individual views. To address these issues, we propose the enhancing Trusted multi-view classification via Evolutionary multi-view Fusion (TEF) approach. TEF employs an evolutionary multi-view architecture search method to create a high-quality fusion architecture serving as the pseudo view, facilitating adaptive view and fusion operator selection. Furthermore, TEF enhances each view within the fusion architecture by concatenating the fusion architecture's decision output with its respective view. Our experimental results demonstrate the effectiveness of this straightforward yet powerful strategy in mitigating imbalanced multi-view learning issues, particularly on complex many-view datasets exceeding three views. Extensive evaluations across 13 multi-view datasets validate the superior performance of our proposed method compared to other trusted multi-view learning approaches. The code is available at https://github.com/fupinhan123/TEF.

Automatic Modulation Classification (AMC) serves as a foundational pillar for cognitive radio systems, enabling critical functionalities including dynamic spectrum allocation, non-cooperative signal surveillance, and adaptive waveform optimization. However, practical deployment of AMC faces a fundamental challenge: prediction ambiguity arising from intrinsic similarity among modulation schemes and exacerbated under low signal-to-noise ratio (SNR) conditions. This phenomenon manifests as near-identical probability distributions across confusable modulation types, significantly degrading classification reliability. To address this, we propose Fuzzy Regularization-enhanced AMC (FR-AMC), a novel framework that integrates uncertainty quantification into the classification pipeline. The proposed FR has three features: (1) Explicitly model prediction ambiguity during backpropagation, (2) dynamic sample reweighting through adaptive loss scaling, (3) encourage margin maximization between confusable modulation clusters. Experimental results on benchmark datasets demonstrate that the FR achieves superior classification accuracy and robustness compared to compared methods, making it a promising solution for real-world spectrum management and communication applications.

Multi-view classification (MVC) based on the Dempster-Shafer theory has gained significant recognition for its reliability in safety-critical applications. However, existing methods predominantly focus on providing confidence levels for decision outcomes without explaining the reasoning behind these decisions. Moreover, the reliance on first-order statistical magnitudes of belief masses often inadequately capture the intrinsic uncertainty within the evidence. To address these limitations, we propose a novel framework termed Trusted Multi-view Classification Constrained with Expert Knowledge (TMCEK). TMCEK integrates expert knowledge to enhance feature-level interpretability and introduces a distribution-aware subjective opinion mechanism to derive more reliable and realistic confidence estimates. The theoretical superiority of the proposed uncertainty measure over conventional approaches is rigorously established. Extensive experiments conducted on three multi-view datasets for sleep stage classification demonstrate that TMCEK achieves state-of-the-art performance while offering interpretability at both the feature and decision levels. These results position TMCEK as a robust and interpretable solution for MVC in safety-critical domains. The code is available at https://github.com/jie019/TMCEK_ICML2025.

Deep learning excels at capturing complex data representations, yet quantifying the discriminative quality of these representations remains challenging. While unsupervised metrics often assess pairwise sample similarity, classification tasks fundamentally require class-level discrimination. To bridge this gap, we propose a novel loss function that evaluates representation discriminability via the Euclidean distance between the learned similarity matrix and the true class adjacency matrix. We identify random consistency—an inherent bias in Euclidean distance metrics—as a key obstacle to reliable evaluation, affecting both fairness and discrimination. To address this, we derive the expected Euclidean distance under uniformly distributed label permutations and introduce its closed-form solution, the Pure Square Euclidean Distance (PSED), which provably eliminates random consistency. Theoretically, we demonstrate that PSED satisfies heterogeneity and unbiasedness guarantees, and establish its generalization bound via the exponential Orlicz norm, confirming its statistical learnability. Empirically, our method surpasses conventional loss functions across multiple benchmarks, achieving significant improvements in accuracy, $F_1$ score, and class-structure differentiation. (Code is published in https://github.com/FeijiangLi/ICML2025-PSED)

Neural architecture search-based multi-modal classification (NAS-MMC) aims to automatically find optimal network structures for improving the multi-modal classification performance. However, most current NAS-MMC methods are quite time-consuming during the training process. In this paper, we propose a knowledge sharing-based neural architecture search (KS-NAS) method for multi-modal classification. The KS-NAS optimizes the search process by introducing a dynamically updated knowledge base to reduce the consumption of computational resource. Specifically, during the deep evolutionary search, individuals in the initial population acquire initial parameters from a knowledge base, and then undergo training and optimization until convergence is reached, avoiding the need for training from scratch. The knowledge base is dynamically updated by aggregating the parameters of high-quality individuals trained within the population, thus progressively improving the quality of the knowledge base. As the population evolves, the knowledge base continues to optimize, ensuring that subsequent individuals can obtain higher-quality initialization parameters, which significantly accelerates the training speed of the population. Experimental results show that the KS-NAS method achieves state-of-the-art results in terms of classification performance and training efficiency across multiple popular multi-modal tasks.

Deep learning-based speech enhancement (SE) methods focus on reconstructing speech from the time or frequency domain. However, these domains cannot provide enough information to capture the dynamics of non-stationary signals accurately. To enrich information, this work proposes a multi-view fusion SE method (MFSE). Specifically, MFSE extends the representation space of speech to the dynamic domain (also called fractional domain) between the time and frequency domains by using the short-time fractional Fourier transform (STFrFT). Subsequently, we construct inputs as modes of the primary short-time Fourier transform (STFT) spectrum and the auxiliary STFrFT spectrum views and adaptively identify the optimal fractional STFrFT spectrum from the infinitely continuous fractional domain by leveraging the average spectral centroids. The framework extracts potential features through multiple designed convolutional modules and captures the correlation between different speech frequencies through multi-granularity attention. Experimental results show that the proposed method significantly improves performance in several metrics compared to existing single-channel SE methods based on time and frequency domains. Furthermore, the results of its generalizability evaluation show that the multi-view method outperforms the single-view method under a wide range of SNR conditions.

In multi-view classification tasks, integrating information from multiple views effectively is crucial for improving model performance. However, most existing methods fail to fully leverage the complex relationships between views, often treating them independently or using static fusion strategies. In this paper, we propose a View-Association-Guided Dynamic Multi-View Classification method (AssoDMVC) to address these limitations. Our approach dynamically models and incorporates the relationships between different views during the classification process. Specifically, we introduce a view-relation-guided mechanism that captures the dependencies and interactions between views, allowing for more flexible and adaptive feature fusion. This dynamic fusion strategy ensures that each view contributes optimally based on its contextual relevance and the inter-view relationships. Extensive experiments on multiple benchmark datasets demonstrate that our method outperforms traditional multi-view classification techniques, offering a more robust and efficient solution for tasks involving complex multi-view data.

Deep learning-based speech enhancement (SE) methods predominantly draw upon two architectural frameworks: generative adversarial networks and diffusion models. In the realm of SE, capturing the local and global relations between signal frames is crucial for the success of these methods. These frameworks typically employ a UNet architecture as their foundational backbone, integrating Long Short-Term Memory (LSTM) networks or attention mechanisms within the UNet to effectively model both local and global signal relations. However, the coupled relation modeling way may not fully harness the potential of these relations. In this paper, we propose an innovative Association-based Fusion Speech Enhancement method (AFSE), a decoupled method. AFSE first constructs a graph that encapsulates the association between each time window of the speech signal, and then models the global relations between frames by fusing the features of these time windows in a manner akin to graph neural networks. Furthermore, AFSE leverages a UNet with dilated convolutions to model the local relations, enabling the network to maintain a high-resolution representation while benefiting from a wider receptive field. Experimental results demonstrate that the AFSE method significantly improves performance in speech enhancement tasks, validating the effectiveness and superiority of our approach. The code is available at https://github.com/jie019/AFSE_IJCAI2025.

Multi-view clustering aims to integrate complementary information from multiple views to improve clustering performance. However, existing ensemble-based methods suffer from information loss due to their reliance on single-granularity labels, limiting the discriminative capability of learned representations. Meanwhile, representation and graph fusion-based approaches face challenges such as explicit view alignment and manual weight tuning, making them less effective for heterogeneous views with varying data distributions. To address these limitations, we propose a novel multi-view clustering framework via Multi-granularity Ensemble (MGE), fully using the multi-granularity information across diverse views for accurate and consistent clustering. Specifically, MGE first modifies the hierarchical clustering and then leverages it on each view (including the fused view) to achieve multi-granularity labels. Moreover, the cross-view and cross-granularity fusion strategy is designed to learn a robust co-association similarity matrix, which effectively preserves the fine-grained and coarse-grained structures of multi-view data and facilitates subsequent clustering. Therefore, MGE can provide a comprehensive representation of local and global patterns within data, eliminating the requirement for view alignment and weight tuning. Experiments demonstrate that MGE consistently outperforms state-of-the-art methods across multiple datasets, validating its effectiveness and superiority in handling heterogeneous views.

View missing remains a significant challenge in graph-based multi-view semi-supervised learning, hindering their real-world applications. To address this issue, traditional methods introduce a missing indicator matrix and focus on mining partial structure among existing samples in each view for label propagation (LP). However, we argue that these disregarded missing samples sometimes induce discontinuous local structures, i.e., sub-clusters, breaking the fundamental smoothness assumption in LP. Consequently, such a Sub-Cluster Problem (SCP) would distort graph fusion and degrade classification performance. To alleviate SCP, we propose a novel incomplete multi-view semi-supervised learning method, termed AGF-TI. Firstly, we design an adversarial graph fusion scheme to learn a robust consensus graph against the distorted local structure through a min-max framework. By stacking all similarity matrices into a tensor, we further recover the incomplete structure from the high-order consistency information based on the low-rank tensor learning. Additionally, the anchor-based strategy is incorporated to reduce the computational complexity. An efficient alternative optimization algorithm combining a reduced gradient descent method is developed to solve the formulated objective, with theoretical convergence. Extensive experimental results on various datasets validate the superiority of our proposed AGF-TI as compared to state-of-the-art methods. Code is available at https://github.com/ZhangqiJiang07/AGF_TI.

Evolutionary multi-view classification (EMVC) methods have gained wide recognition due to their adaptive mechanisms. Fitness evaluation (FE), which aims to calculate the classification performance of each individual in the population and provide reliable performance ranking for subsequent operations, is a core step in such methods. Its accuracy directly determines the correctness of the evolutionary direction. That is, when FE fails to correctly reflect the superiority-inferiority relationship among individuals, it will lead to confusion in individual performance ranking, which in turn misleads the evolutionary direction and results in trapping into local optima. This paper is the first to identify the aforementioned issue in the field of EMVC and call it as fitness evaluation bias (FEB). FEB may be caused by a variety of factors, and this paper approaches the issue from the perspective of view information content: existing methods generally adopt joint training strategies, which restrict the exploration of key information in views with low information content. This makes it difficult for multi-view model (MVM) to achieve optimal performance during convergence, which in turn leads to FE failing to accurately reflect individual performance rankings and ultimately triggering FEB. To address this issue, we propose an evolutionary multi-view classification via eliminating individual fitness bias (EFB-EMVC) method, which alleviates the FEB issue by introducing evolutionary navigators for each MVM, thereby providing more accurate individual ranking. Experimental results fully verify the effectiveness of the proposed method in alleviating the FEB problem, and the EMVC method equipped with this strategy exhibits more superior performance compared with the original EMVC method. (The code is available at https://github.com/LiShuailzn/Neurips-2025-EFB-EMVC)

It is a challenging task to select the informative features that can maintain the manifold structure in the original feature space. Many unsupervised feature selection methods still suffer the poor cluster performance in the selected feature subset. To tackle this problem, a feature subspace learning-based binary differential evolution algorithm is proposed for unsupervised feature selection. Firstly, a new unsupervised feature selection framework based on evolutionary computation is designed, in which the feature subspace learning and the population search mechanism are combined into a unified unsupervised feature selection. Secondly, a local manifold structure learning strategy and a sample pseudo-label learning strategy are presented to calculate the importance of the selected feature subspace. Thirdly, the binary differential evolution algorithm is developed to optimize the selected feature subspace, in which the binary information migration mutation operator and the adaptive crossover operator are designed to promote the searching for the global optimal feature subspace. Experimental results on various types of realworld datasets demonstrate that the proposed algorithm can obtain more informative feature subset and competitive cluster performance compared with eight state-of-the-art unsupervised feature selection methods.

Multi-modal neural architecture search (MNAS) is an effective approach to obtain task-adaptive multi-modal classification models. Deep neural networks, as currently main-stream feature extractors, can provide hierarchical features for each modality. Existing MNAS methods face difficulty in exploiting such hierarchical features due to their different form coexistence such as tensorial multi-scale features and vectorized penultimate features. Moreover, existing methods always focus on the evolution of fusion operators or vectorized features of all modalities, constraining search space. In this paper, a novel two-stage method called multi-modal multi-scale evolutionary neural architecture search (MM-ENAS) is proposed. The first stage unifies the representation form of hierarchical features by the proposed evolutionary statistics strategy. The second stage identifies the optimal combination of basic fusion operations for all unified hierarchical features by the evolutionary algorithm. MM-ENAS increases search space by simultaneously searching for feature statistical extraction methods, basic fusion operators and feature representation set consisting of tensorial multi-scale features and vectorized penultimate features. Experimental results on three multi-modal tasks demonstrate that the proposed method achieves competitive performance in terms of accuracy, search time, and number of parameters compared to existing representative MNAS methods. Additionally, the method exhibits fast adaptation to various multi-modal tasks.

To partition samples into distinct clusters, Fuzzy C-Means (FCM) calculates the membership degrees of samples to cluster centers and provides soft labels, gaining significant attention in recent years. However, existing FCM methods encounter the following challenges. First, traditional FCM focuses on learning membership degrees, neglecting the data similarity structures. Second, graph-based FCM typically separates graph construction from clustering, overlooking the knowledge interaction between graphs and clustering, obtaining suboptimal performance. Third, exploring the similarity structures among all samples is computationally expensive for large-scale tasks. To solve these dilemmas, we propose a scalable fuzzy clustering with collaborative structure learning and preservation (CSLP), which simultaneously leverages both cluster information and similarity structures to learn an optimal membership degree representation. Specifically, a self-weighted manner is devised to measure the sample importance, thereby reducing the adverse impacts of outliers. Moreover, the graph is updated according to the data similarities in the membership degree representation, such that CSLP collaboratively learns the graph and membership degrees in a mutually reinforcing manner. Thus, the similarity structures are fully explored during clustering processes and preserved in the learned membership degrees, enhancing the discrimination of clustering labels. To further improve efficiency, an acceleration solution is developed to reduce the computational cost of CSLP by propagating membership degrees from potential centers to samples, making CSLP scalable for large-scale tasks. An iterative strategy is designed to solve the formulated objective function. Extensive experiments demonstrate that CSLP outperforms other fuzzy clustering methods in terms of both effectiveness and scalability.

Classification tasks have long been a central concern in the field of machine learning. Although deep neural network-based approaches offer a novel, versatile and highly precise solution for classification tasks, the intrinsic ambiguity and uncertainty present in the data continue to pose a significant challenge, impeding the potential for further advancements in classification accuracy. To address this issue, we propose a Fuzzy neurAl SupporT vEctor machiNe (FASTEN) which mitigates the fuzziness and uncertainty inherent in the data and enhances the classification performance. FASTEN mainly consists of two parts: the fuzzy feature extraction unit and the multi-path classifier aggregation unit. The fuzzy feature extraction unit is designed to precisely capture the fuzzy features of the uncertainty data by embedding membership functions and fuzzy rules within the neural network. In this process, fuzzy parameters are dynamically updated on a task-driven basis, ensuring that the model can adaptively handle data with different degrees of fuzziness. The multi-path classifier aggregation unit is designed to integrate the outputs of multiple neural network classifiers through dynamic linear combination. Meanwhile, we introduce the maximum margin theory of support vector machines to optimize the feature representation and improve classification accuracy. Our experimental results show that FASTEN can improve the classification performance on image and signal datasets. Through ablation experiments, the contributions of each unit to performance enhancement have been further validated, thereby establishing a foundation for subsequent model optimization.

Due to the efficiency of integrating semantic consensus and complementary information across different views, multi-view classification methods have attracted much attention in recent years. However, multi-view data often suffers from both the miss of view features and insufficient label information, which significantly decrease the performance of traditional multi-view classification methods in practice. Learning for such simultaneous lack of feature and label is crucial but rarely studied. To tackle these problems, we propose a novel Deep Incomplete Multi-view Learning Network (DIMvLN) by incorporating graph networks and semi-supervised learning in this paper. Specifically, DIMvLN firstly designs the deep graph networks to effectively recover missing data with assigning pseudo-labels of large amounts of unlabeled instances and refine the incomplete feature information. Meanwhile, to enhance the label information, a novel pseudo-label generation strategy with the similarity constraints of unlabeled instances is proposed to exploit additional supervisory information and guide the completion module to preserve more semantic information of absent multi-view data. Besides, we design view-specific representation extractors with the autoencoder structure and contrastive loss to learn high-level semantic representations for each view, promote cross-view consistencies and augment the separability between different categories. Finally, extensive experimental results demonstrate the effectiveness of our DIMvLN, attaining noteworthy performance improvements compared to state-of-the-art competitors on several public benchmark datasets. Code will be available at GitHub.

Neural architecture search-based multi-modal classification (NAS-MMC) methods can individually obtain the optimal classifier for different multi-modal data sets in an automatic manner. However, most existing NAS-MMC methods are dramatically time consuming due to the requirement for training and evaluating enormous models. In this paper, we propose an efficient evolutionary-based NAS-MMC method called divide-and-conquer neural architecture search (DC-NAS). Specifically, the evolved population is first divided into k+1 sub-populations, and then k sub-populations of them evolve on k small-scale data sets respectively that are obtained by splitting the entire data set using the k-fold stratified sampling technique; the remaining one evolves on the entire data set. To solve the sub-optimal fusion model problem caused by the training strategy of partial data, two kinds of sub-populations that are trained using partial data and entire data exchange the learned knowledge via two special knowledge bases. With the two techniques mentioned above, DC-NAS achieves the training time reduction and classification performance improvement. Experimental results show that DC-NAS achieves the state-of-the-art results in term of classification performance, training efficiency and the number of model parameters than the compared NAS-MMC methods on three popular multi-modal tasks including multi-label movie genre classification, action recognition with RGB and body joints and dynamic hand gesture recognition.

Most existing NAS-based multi-modal classification (MMC-NAS) methods are optimized using the classification accuracy.They can not simultaneously provide multiple models with diverse perferences such as model complex and classification performance for meeting different users' demands. Combining NAS-MMC with multi-objective optimization is a nature way for this issue. However, the challenge problem of this solution is the high computation cost. For multi-objective optimization, the computing bottleneck is pareto front search. Some higher-quality MMC models (namely core structures, CSs) consisting of high-quality features and fusion operators are easier to identify. We find that CSs have a close relation with the pareto front (PF), i.e., the individuals lying in PF contain the CSs. Based on the finding, we propose an efficient multi-objective neural architecture search for multi-modal classification by applying CSs to guide the PF search (CoMO-NAS). In conclusion, experimental results thoroughly demonstrate the effectiveness of our CoMO-NAS. Compared to state-of-the-art competitors on benchmark multi-modal tasks, we achieve comparable performance with lower model complexity in shorter search time.

In multi-modal classification tasks, a good fusion algorithm can effectively integrate and process multi-modal data, thereby significantly improving its performance. Researchers often focus on the design of complex fusion operators and have proposed numerous fusion operators, while paying less attention to the design of feature fusion usage, specifically how features should be fused to better facilitate multi-modal classification tasks. In this article, we propose a progressive skip reasoning fusion network (PSRFN) to make some attempts to address this issue. Firstly, unlike most existing multi-modal fusion methods that only use one fusion operator in a single stage to fuse all view features, PSRFN utilizes the progressive skip reasoning (PSR) block to fuse all views with a fusion operator at each layer. Specifically, each PSR block utilizes all view features and the fused features from the previous layer to jointly obtain the fused features for the current layer. Secondly, each PSR block utilizes a dual-weighted fusion strategy with learnable parameters to adaptively allocate weights during the fusion process. The first level of weighting assigns weights to each view feature, while the second level assigns weights to the fused features from the previous layer and the fused features obtained from the first level of weighting in the current layer. This strategy ensures that the PSR block can dynamically adjust the weights based on the actual contribution of features. Finally, to enable the model to fully utilize feature information from different levels for feature fusion, the skip connections are adopted between PSR blocks. Extensive experiment results on six real multi-modal datasets show that a better usage for fusion operator is indeed able to improve performance.

To tackle the high-dimensional data with multiple representations, multi-view unsupervised feature selection has emerged as a significant learning paradigm. However, previous methods suffer from the following dilemmas: (i) They focus on selecting the features that preserve the similarity structure of data, whereas neglecting the discriminative information in the cluster structure; (ii) The orthogonal constraint is often imposed on the pseudo cluster labels, breaking the locality in the cluster label space; (iii) Learning the similarity or cluster structure from all samples is time-consuming. To this end, a Scalable Multi-view Unsupervised Feature Selection with structure learning and fusion (SMUFS) is proposed to jointly exploit the cluster structure and the similarity relations of data. Specifically, SMUFS introduces the sample-view weights to adaptively fuse the membership matrices that indicate cluster structures and serve as the pseudo cluster labels, such that a unified membership matrix across views can be effectively obtained to guide feature selection. Meanwhile, SMUFS performs graph learning from the membership matrix, preserving the locality of cluster labels and improving their discriminative capability. Further, an acceleration strategy has been developed to make SMUFS scalable for large-scale data. An iterative optimization is designed to solve the formulated objective function, and extensive experiments demonstrate the superiority of SMUFS.

Multi-task learning uses knowledge transfer among tasks to improve the generalization performance of all tasks. For deep multi-task learning, knowledge transfer is often implemented via sharing all hidden features of tasks. A major shortcoming is that it can lead to negative knowledge transfer across tasks when task correlation is weak. To overcome it, this paper proposes an evolutionary method to learn sparse sharing representations adaptively. By embedding the neural network optimization into evolutionary multitasking, our proposed method finds an optimal combination of tasks and sharing features. It can identify negative correlation and redundant features and then remove them from the hidden feature set. Thus, an optimal sparse sharing subnetwork can be produced for each task. Experiment results show that the proposed method achieve better learning performance with a smaller inference model than other related methods.

Speaker verification is a natural and effective biometric authentication method. This method may be more practical when trained using data from real, unconstrained scenarios. However, although the speech quality from real scenarios varies because of various adverse factors, including extreme noise and the lack of identity information, most models treat all speech samples equally. To tackle this deficiency, we propose adaptive weight loss (AWL), a function that assigns different weights to samples in accordance with their quality and difficulty based on our finding that speech quality is positively correlated with the L2 norm of speaker embedding. AWL directs the model's attention to high-quality difficult speech samples and ignores low-quality difficult samples as much as possible so that the model can learn well from speech data containing a lot of noise. Comprehensive experiments reveal that AWL significantly outperforms existing loss functions on both utilized public and noisy datasets.

Multi-modal classification (MMC) aims to integrate the complementary information from different modalities to improve classification performance. Existing MMC methods can be grouped into two categories: traditional methods and deep learning-based methods. The traditional methods often implement fusion in a low-level original space. Besides, they mostly focus on the inter-modal fusion and neglect the intra-modal fusion. Thus, the representation capacity of fused features induced by them is insufficient. The deep learning-based methods implement the fusion in a high-level feature space where the associations among features are considered, while the whole process is implicit and the fused space lacks interpretability. Based on these observations, we propose a novel interpretative association-based fusion method for MMC, named AF. In AF, both the association information and the high-order information extracted from feature space are simultaneously encoded into a new feature space to help to train an MMC model in an explicit manner. Moreover, AF is a general fusion framework, and most existing MMC methods can be embedded into it to improve their performance. Finally, the effectiveness and the generality of AF are validated on 22 datasets, four typically traditional MMC methods adopting best modality, early, late and model fusion strategies and a deep learning-based MMC method.

Feature extraction is a critical issue in many machine learning systems. A number of basic fusion operators have been proposed and studied. This article proposes an evolutionary algorithm, called evolutionary deep fusion method, for searching an optimal combination scheme of different basic fusion operators to fuse multiview features. We apply our proposed method to chemical structure recognition. Our proposed method can directly take images as inputs, and users do not need to transform images to other formats. The experimental results demonstrate that our proposed method can achieve a better performance than those designed by human experts on this real-life problem.