Luoyang Sun, Guangyan Li, Cheng Deng, Haifeng Zhang, Jian Zhao, Yongqiang Tang, Wensheng Zhang, Jun Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large Language Models (LLMs) have demonstrated strong capabilities in web search and reasoning. However, their dependence on static training corpora makes them prone to factual errors and knowledge gaps. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge sources, especially structured Knowledge Graphs (KGs), which provide explicit semantics and efficient retrieval. Existing KG-based RAG approaches, however, generally assume that anchor entities are accessible to initiate graph traversal, which limits their robustness in open-world settings where accurate linking between the user query and the KG entity is unreliable. To overcome this limitation, we propose AnchorRAG, a novel multi-agent collaboration framework for open-world RAG without the predefined anchor entities. Specifically, a predictor agent dynamically identifies candidate anchor entities by aligning user query terms with KG nodes and initializes independent retriever agents to conduct parallel multi-hop explorations from each candidate. Then a supervisor agent formulates the iterative retrieval strategy for these retriever agents and synthesizes the resulting knowledge paths to generate the final answer. This multi-agent collaboration framework improves retrieval robustness and mitigates the impact of ambiguous or erroneous anchors. Extensive experiments on four public benchmarks demonstrate that AnchorRAG significantly outperforms existing baselines and establishes new state-of-the-art results on the real-world reasoning tasks.

The remarkable success of GNNs has provoked the challenge of high computational and memory overhead when training with large-scale graphs. As a promising solution, graph condensation is committed to constructing synthetic graphs with significantly smaller size, which are expected to preserve the essential characteristics of the original ones. During this process, a core problem is how to accurately portray and align the data distribution structures between the original graph space and the synthetic graph space. A mainstream idea in existing research is matching the class distributions between the two spaces. Unfortunately, they generally overlook two key issues: 1) heterophilic nodes in original graphs may render the chaotic class distribution patterns; 2) coarse-grained matching of the overall class centroid between original and synthetic spaces is insufficient for data with complex subcategory distributions. In this paper, we propose a novel Graph Condensation method via homophily node Refinement and fine-grained class Distribution matching (GCRD). Given the original large-scale graph, we first distinguish the nodes into advantageous homophilic nodes and detrimental heterophilic nodes, followed by adaptively assigning node weights to refine the generated class distribution patterns of the original graphs. Furthermore, with the refined class distribution patterns, we propose a fine-grained distribution matching objective to more delicately align the local distribution structure of subclasses within each class. The rigorous theoretical analysis confirms the effectiveness of our proposal in precisely learning the class information. Extensive experiments demonstrate our state-of-the-art classification and cross-architecture generalization performance against various baselines.

Spatially resolved transcriptomics (SRT) enables the simultaneous capture of gene expression profiles and spatial localization, providing valuable insights into tissue architecture. However, the preservation of spatial information requires additional experimental procedures, which often introduce substantial technical noise. Existing methods typically perform denoising and spatial domain identification in separate steps, leading to suboptimal performance and limiting their applicability. To address this limitation, we propose an integrative network model, stACN ( spatial transcriptomics Attribute Cell Network), that jointly denoises gene expression data and identifies spatial domains in SRT. Specifically, stACN first learns clean dual cell networks using a graph noise model, and then derives compatible cell features through joint tensor decomposition of the denoised networks. Experimental results demonstrate that stACN effectively enhances data quality, as measured by clustering agreement with reference annotations (Adjusted Rand Index, ARI), and facilitates spatial domain analysis in SRT datasets.

In recent years, the advancements in large vision-language models (VLMs) like CLIP have sparked a renewed interest in leveraging the prompt learning mechanism to preserve semantic consistency between source and target domains in unsupervised domain adaption (UDA). While these approaches show promising results, they encounter fundamental limitations when quantifying the similarity between source and target domain data , primarily stemming from the redundant and modality-missing class centroids . To address these limitations, we propose P rompt-affinity M ulti-modal C lass C entroids for UDA (termed as PMCC). Firstly, we fuse the text class centroids (directly generated from the text encoder of CLIP with manual prompts for each class) and image class centroids (generated from the image encoder of CLIP for each class based on source domain images) to yield the multi-modal class centroids. Secondly, we conduct the cross-attention operation between each source or target domain image and these multi-modal class centroids. In this way, these class centroids that contain rich semantic information of each class will serve as a bridge to effectively measure the semantic similarity between different domains. Finally, we design a logit bias head and employ a multi-modal prompt learning mechanism to accurately predict the true class of each image for both source and target domains. We conduct extensive experiments on 4 popular UDA datasets including Office-31, Office-Home, VisDA-2017, and DomainNet. The experimental results validate our PMCC achieves higher performance with lower model complexity than the state-of-the-art (SOTA) UDA methods. The code of this project is available at GitHub: https://github.com/246dxw/PMCC .

Low-light image enhancement aims to restore visibility, contrast, and semantic fidelity to images captured under poor illumination, which often suffer from uneven lighting, detail loss, and noise. Most existing deep learning methods usually rely on paired datasets, which limits their generalization ability. To overcome these limitations, a new zero-shot low-light enhancement network, termed BRSGNet, is introduced to improve brightness-aware representation and enhance semantic consistency. Specifically, a Brightness-Aware Module (BAM) with multi-scale dilated convolution and spatial attention mechanisms is designed to improve illumination estimation while preserving global-local details. Then, a Semantic-Aware Network (SANet) incorporating a Semantic Feature Consistency Loss (SFC-Loss) is introduced to enforce semantic alignment between the enhanced and original images without requiring ground-truth references. Extensive experiments on three public benchmarks demonstrate that the proposed approach achieves competitive performance in terms of both visual quality and semantic consistency, showcasing strong generalization across diverse low-light conditions.

Different from the traditional semi-supervised learning paradigm that is constrained by the close-world assumption, Generalized Category Discovery (GCD) presumes that the unlabeled dataset contains new categories not appearing in the labeled set, and aims to not only classify old categories but also discover new categories in the unlabeled data. Existing studies on GCD typically devote to transferring the general knowledge from the self-supervised pretrained model to the target GCD task via some fine-tuning strategies, such as partial tuning and prompt learning. Nevertheless, these fine-tuning methods fail to make a sound balance between the generalization capacity of pretrained backbone and the adaptability to the GCD task. To fill this gap, in this paper, we propose a novel adapter-tuning-based method named AdaptGCD, which is the first work to introduce the adapter tuning into the GCD task and provides some key insights expected to enlighten future research. Furthermore, considering the discrepancy of supervision information between the old and new classes, a multi-expert adapter structure equipped with a route assignment constraint is elaborately devised, such that the data from old and new classes are separated into different expert groups. Extensive experiments are conducted on 7 widely-used datasets. The remarkable performance improvements highlight the efficacy of our proposal and it can be also combined with other advanced methods like SPTNet for further enhancement.

Survival analysis is extensively employed to analyze the probability of the event of interest, particularly in the medical field. Most current research treats patients as isolated entities, neglecting the complex associations among them, which leads to underutilization of valuable information. Recently, several studies address this limitation by incorporating patient graph structures. However, these approaches generally overlook two critical issues: 1) the exploration of heterogeneous inter-patient relationships, and 2) flexible and scalable inductive inference for test samples. To overcome these challenges, this study introduces a novel framework, Multiplex Graph Guided Deep Survival Analysis (MGG-Surv). Specifically, we employ multiplex patient graphs to capture comprehensive inter-patient associative information. Furthermore, we propose a teacher-student dual network architecture, where the teacher network encodes multiplex graphs, and the learned graph knowledge is transferred to the student network via a unidirectional connection termed Graph-Guided Distillation. The student network integrates this graph knowledge to predict survival outcomes without requiring the patient graphs. These innovative designs facilitate comprehensive integration of inter-patient relationships while achieving flexible and scalable graph-free inference. Experiments on four datasets, encompass-ing both single and competing risks, demonstrate the superior performance of our framework.

Recently, most image-text matching (ITM) approaches have embraced a dual-stream transformer architecture to facilitate the learning and alignment of cross-modal semantic information. Despite the efficacy of this methodology in bridging the semantic disparity between images and texts, it exhibits two primary limitations. Firstly, it falls short in discriminating the nuanced similarities among features, which leads to misleading outcomes or even compromises the overall ITM process. Secondly, the conventional triplet training paradigm relies on a pre-determined, fixed margin coefficient, thereby impeding its capacity to accurately gauge the similarity relationships between positive and negative samples. In this article, we propose high feature D istinguishability for A daptive I mage-text M atching with dual-stream transformers (termed as DAIM). To address the first limitation, we design a feature discriminability module to bring similar features closer together but with a certain degree of distinction and push dissimilar features farther apart, resulting in high feature distinguishability for accurate ITM. To address the second limitation, we devise a margin optimization module to perceive the similarity distribution between positive and negative samples in real-time during training, thereby adaptively adjusting the margin coefficient to minimize the cross-modal semantic gap to the greatest extent possible. Based on this, we align the multi-level (i.e., representations from low-, middle-, and high-layer transformer encoders) semantic information of cross-modal data by adaptively optimizing the semantic distributions of positive and negative samples. We conduct extensive experiments on two commonly used benchmark datasets, including MSCOCO and Flickr30K. Experimental results verify that DAIM can achieve a higher performance (e.g., 4.7% RSUM gain on MSCOCO) than the state-of-the-art ITM methods. The open-sourced code of this project is available at: https://github.com/Hudjkfhdsjfhdjkg/DAIM.git .

Graph Neural Networks (GNNs) have been proven effective in modeling graph data, mostly depending on the in-distribution assumption. While in the out-of-distribution (OOD) scenarios, especially for the more challenging node-level task, the feature and structure distribution shifts between training and test nodes lead to performance degradation. To improve node-level OOD generalization, typical approaches introduce graph augmentation to enrich the training environments and conduct invariant learning to learn stable representations across various augmented environments. However, their graph augmentations emphasize diversity but neglect the preservation of invariant patterns which are fundamental to invariant learning. Moreover, most of them simply conduct the classic invariant learning objective but lack the consideration of the graph-specific structure information. Therefore, to mitigate their weakness, we propose a Structure-aware Invariant learning framework for Node-level Graph OOD generalization (SING). Specifically, we develop the invariance constraint regularization terms during the optimization of augmentations. Additionally, we define the structure embedding to elucidate the structural property and design the structure embedding alignment loss to optimize the augmentations and the invariant representations. By introducing the structure information, we further integrate the unique structural property into invariant learning, thereby boosting the invariant message-passing GNNs. The extensive experiments on the transductive GOOD benchmark and the inductive datasets empirically validate our superior OOD generalization performance to baselines.

Due to the thermal noise caused by heat diffusion during the imaging process, the edge shape of the infrared small target detection (IRSTD) in remote sensing becomes blurred. This degrades the performance of the subsequent feature extraction. To address such a problem, we propose three modules based on deep learning. First, we design a heat equation block (HEB) by combining the heat equation in the frequency domain with a convolutional network to reproduce heat diffusion on the image. Then, a graph attention filter (GAF) is designed, which aggregates the graph node features and adjacent difference features of the graph structure. By learning the change of the features before and after the diffusion, thermal noise is reduced. Moreover, the multiscale features are fused through customized multiscale residual fusion block (MRFB). Experimental results show that the proposed method achieves an intersection over union (IoU) of 80.01% and 69.20% on the NUAA-SIRST and IRSTD-1K datasets, respectively, outperforming other advanced methods and verifying the effectiveness of the proposed method in remote sensing under various and complex backgrounds.

Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and protecting old knowledge, leading to zero-shot generalization collapse, and cross-modal hallucination. In this paper, we reformulate Adapter, LoRA, Prefix-tuning, and Prompt-tuning from the perspective of gradient projection, and first propose a unified framework called Parameter Efficient Gradient Projection (PEGP). We introduce orthogonal gradient projection into different PET paradigms and theoretically demonstrate that the orthogonal condition for the gradient can effectively resist forgetting even for large-scale models. It therefore modifies the gradient towards the direction that has less impact on the old feature space, with less extra memory space and training time. We extensively evaluate our method with different backbones, including ViT and CLIP, on diverse datasets, and experiments comprehensively demonstrate its efficiency in reducing forgetting in class, online class, domain, task, and multi-modality continual settings.

The significant success of graph learning has provoked a meaningful but challenging task of extracting the precise causal subgraphs that can interpret and improve the predictions. Unfortunately, current works merely center on partially eliminating either the spurious or the noisy parts, while overlook the fact that in more practical and general situations, both the spurious and noisy subgraph coexist with the causal one. This brings great challenges and makes previous methods fail to extract the true causal substructure. Unlike existing studies, in this paper, we propose a more reasonable problem formulation that hypothesizes the graph is a mixture of causal, spurious, and noisy subgraphs. With this regard, an Information Bottleneck-constrained denoised Causal Subgraph (IBCS) learning model is developed, which is capable of simultaneously excluding the spurious and noisy parts. Specifically, for the spurious correlation, we design a novel causal learning objective, in which beyond minimizing the empirical risks of causal and spurious subgraph classification, the intervention is further conducted on spurious features to cut off its correlation with the causal part. On this basis, we further impose the information bottleneck constraint to filter out label-irrelevant noise information. Theoretically, we prove that the causal subgraph extracted by our IBCS can approximate the ground-truth. Empirically, extensive evaluations on nine benchmark datasets demonstrate our superiority over state-of-the-art baselines.

Dynamic link prediction (DLP) plays a critical role in understanding and forecasting evolving relationships in real-world systems across various domains. However, accurately predicting future links remains challenging, as existing methods often overlook the independent modeling of dynamic interactions within individual nodes and the fine-grained characterization of latent interactions across node sequences. To address these challenges, we propose FineFormer (Fine-grained Interactive Transformer), a novel framework that alternates between self-attention and cross-attention mechanisms, enhanced with layer-wise contrastive learning. This design enables FineFormer to uncover fine-grained temporal dependencies both within single node sequences and across different node sequences. Specifically, self-attention captures temporal-spatial dynamics within the interaction sequences of individual nodes, while cross-attention focuses on the complex interactions across the sequences of pairs of nodes. Additionally, by strategically applying layer-wise contrastive learning, FineFormer refines node representations and enhances the model's ability to distinguish between connected and unconnected node pairs during feature refinement. FineFormer is evaluated on five challenging and diverse real-world DLP datasets. Experimental results demonstrate that FineFormer consistently outperforms state-of-the-art baselines, particularly in capturing complex, fine-grained interactions in continuous-time dynamic networks.

Traditional Chinese Medicine (TCM) boasts a long history and a unique diagnostic and therapeutic paradigm. Integrating TCM with Western medicine and modern medical devices has yielded numerous successful cases in recent years. TCM treatment has developed a special knowledge framework focusing on precise differentiation based on multidimensional information such as the patient's diseases, symptoms, and syndromes. This offers significant opportunities for AI research in similar patient scenarios within TCM contexts. However, traditional medicine's reliance on the physiological sensory judgment of human physicians to gather clinical information might lead to non-standardized descriptions and disturbances in patient assessments. Additionally, how to integrate TCM's fine-grained differentiation knowledge to design a patient similarity measure remains an open question. To address this, we first constructed a real-world dataset of TCM gastrointestinal malignancies (TCMGI) based on real cases in the Guang'anmen Hospital, China Academy of Chinese Medical Sciences. It contains 406 types of multidimensional information from 719 patients, organized in a graph structure. Second, we develop a novel deep learning framework, Robust Traditional Chinese Medicine Graph Networks (RTGN), which employs a Siamese network architecture with self-attention and self-supervision strategies to enhance robustness in patient retrieval. Lastly, we design a patient similarity metric integrating TCM and Western medicine approaches, demonstrating superior performance in depicting fine-grained patient similarities. Experimental results show our method outperforms existing best practices in patient retrieval accuracy. Moreover, the proposed similarity metric exhibits excellent performance in clustering tasks at various granularity levels, possibly supporting precision TCM patient retrieval and downstream tasks, such as prescription generation.

Immune thrombocytopenia (ITP) is a typically self-limiting and immune-mediated bleeding disorder in children. Approximately 20% of children with ITP experience chronicity, leading to reduced quality of life and increased treatment burden. The accurate prediction of chronicity would enable clinicians to make personalized treatment plans at an early stage. However, due to the self-limiting nature of ITP and the scarcity of available children patients, the data presents two prominent issues: small data and imbalanced class, which are unfavorable for effectively training a deep learning model. To handle these issues concurrently, we proposed a novel method that integrates contrastive learning with the Transformer. First, we adopt the FT-Transformer as our backbone, which allows our model to flexibly process heterogeneous tabular data. Second, we amplify and balance the original data via random masking and oversampling, respectively. Lastly, we build contrastive pairs according to the latent representations generated by the FT-Transformer encoder, such that the amplified and oversampled synthetic data can be utilized thoroughly. The experimental results on real-world ITP children data show that our proposal outperforms the state-of-the-art methods, and demonstrate the significant advantages of dealing with insufficient and imbalanced problems.

Alignment between the food images and the corresponding recipes is an emerging cross-modal representation learning task. In this task, the recipes are composed of three components, i.e., food title, ingredient lists, and cooking instructions, which require a fine-grained alignment between the features of the two modalities. Existing methods usually aggregate the recipes into global embeddings and then align them with the global image embeddings. Meanwhile, semantic classification is frequently used in these methods to regularize the embeddings of the two modalities. While these methods are efficient, there remain two problems: (1) Forcing the alignment between the global images and recipes embeddings may result in losing the component-specific information. (2) The high diversity of food appearance leads to high uncertainty in the semantic classification of food images and recipes. To solve these problems, we propose a Fine-grained Prompting and Alignment (FPA) model to enhance the feature extraction and bring more component-specific information for fine-grained alignment. Furthermore, to regularize the semantic information contained in the cross-modal features, we design an Evidential Semantic Consistency (ESC) loss to keep the cross-modal semantic consistency. We have conducted comprehensive experiments on the benchmark dataset Recipe1M and the state-of-the-art results on the cross-modal recipe retrieval task demonstrate the effectiveness of our method.

As a recent noticeable topic, domain generalization aims to learn a generalizable model on multiple source domains, which is expected to perform well on unseen test domains. Great efforts have been made to learn domain-invariant features by aligning distributions across domains. However, existing works are often designed based on some relaxed conditions which are generally hard to satisfy and fail to realize the desired joint distribution alignment. In this article, we propose a novel domain generalization method, which originates from an intuitive idea that a domain-invariant classifier can be learned by minimizing the Kullback-Leibler (KL)-divergence between posterior distributions from different domains. To enhance the generalizability of the learned classifier, we formalize the optimization objective as an expectation computed on the ground-truth marginal distribution. Nevertheless, it also presents two obvious deficiencies, one of which is the side-effect of entropy increase in KL-divergence and the other is the unavailability of ground-truth marginal distributions. For the former, we introduce a term named maximum in-domain likelihood to maintain the discrimination of the learned domain-invariant representation space. For the latter, we approximate the ground-truth marginal distribution with source domains under a reasonable convex hull assumption. Finally, a constrained maximum cross-domain likelihood (CMCL) optimization problem is deduced, by solving which the joint distributions are naturally aligned. An alternating optimization strategy is carefully designed to approximately solve this optimization problem. Extensive experiments on four standard benchmark datasets, i.e., Digits-DG, PACS, Office-Home, and miniDomainNet, highlight the superior performance of our method.

Despite recent progress in semi-supervised learning (SSL), its scalability remains limited in realistic scenarios where unseen classes may appear in the unlabeled data. To address this challenge, open-world SSL (OWSSL) is proposed in recent years and attracts much attention. One core difficulty in OWSSL is to enhance the representative ability for unlabeled samples, especially for those in novel classes. More recently, several works introduce contrastive learning into OWSSL and achieve impressive performance. However, they mainly focus on conducting contrastive learning solely in either feature or prediction spaces, while ignoring the thorough exploration of information potentials in dual spaces. In this study, we propose a novel method to handle OWSSL tasks via dual-space contrastive learning (DSCL). DSCL contains two modules: intraspace contrastive learning and interspace contrastive learning. In the intraspace module, we bridge the two spaces with a learnable classifier and impose contrastive learning in the dual spaces, such that the category discriminative information could be effectively utilized to improve the representative ability. In interspace module, to further enhance the utilization of complementary information from dual spaces, we introduce neighborhood information from feature space to enhance predictive learning and meanwhile utilize the cluster structure from the prediction spaces to improve intraclass compactness of the features. Compared with state-of-the-art competitors, the proposed DSCL achieves superior performance on the popular benchmarks, i.e., CIFAR100, Imagenet100, CIFAR10, CUB-200, and Scar.

Multiplex graph representation learning has attracted considerable attention due to its powerful capacity to depict multiple relation types between nodes. Previous methods generally learn representations of each relation-based subgraph and then aggregate them into final representations. Despite the enormous success, they commonly encounter two challenges: 1) the latent community structure is overlooked and 2) consistent and complementary information across relation types remains largely unexplored. To address these issues, we propose a clustering-enhanced multiplex graph contrastive representation learning model (CEMR). In CEMR, by formulating each relation type as a view, we propose a multiview graph clustering framework to discover the potential community structure, which promotes representations to incorporate global semantic correlations. Moreover, under the proposed multiview clustering framework, we develop cross-view contrastive learning and cross-view cosupervision modules to explore consistent and complementary information in different views, respectively. Specifically, the cross-view contrastive learning module equipped with a novel negative pairs selecting mechanism enables the view-specific representations to extract common knowledge across views. The cross-view cosupervision module exploits the high-confidence complementary information in one view to guide low-confidence clustering in other views by contrastive learning. Comprehensive experiments on four datasets confirm the superiority of our CEMR when compared to the state-of-the-art rivals.

Recently, as one of the most popular covert communication technologies, generative steganography has received ever-increasing attention due to its promising performance against sophisticated steganalysis tools. However, it is quite difficult for the existing generative steganographic approaches to find a good tradeoff between hiding capacity and extraction accuracy, mainly due to the small capacity of their hiding spaces. To overcome this shortcoming, a Progressive Generative Steganography (PGS) network architecture is proposed to hide a secret message during the progressive image generation process to realize secure covert communication. Specifically, we first propose a robust Secret-to-Noise (S2N) mapping method to encode the secret message as a set of noise maps. Then, guided by these noise maps, a set of corresponding images ranging from low resolution to high resolution are progressively generated by the Single Generative Adversarial Networks (SINGAN). Consequently, a large-sized secret message can be hidden in the finally generated high-resolution image, since a set of high-capacity hiding spaces can be provided by the process of progressive image generation. Moreover, to improve the quality of image generation and the accuracy of secret message extraction, a Dense Secret-Feature Connection (DSFC) strategy is designed and integrated into the proposed PGS network architecture. Extensive experiments demonstrate that the proposed PGS outperforms the existing approaches in the aspects of both hiding capacity and message extraction, while maintaining promising anti-detectability and imperceptibility for covert communication.

Large language models (LLMs) show excellent performance in difficult tasks, but they often require massive memories and computational resources. How to reduce the parameter scale of LLMs has become research hotspots. In this study, we get an important observation that the multi-head self-attention (MHA) sub-layer of Transformer exhibits noticeable low-rank structure, while the feed-forward network (FFN) sub-layer does not. With this regard, we design a novel structured compression method LoRAP, which organically combines Low-Rank matrix approximation And structured Pruning. For the MHA sub-layer, we proposal an input activation weighted singular value decomposition method and allocate different parameter amounts for each weight matrix based on the differences in low-rank properties of matrices.For the FFN sub-layer, we propose a gradient-free structured channel pruning method and save the least important 1% of parameters which actually play a vital role in model performance. Extensive evaluations on zero-shot perplexity and zero-shot task classification indicate that our proposal is superior to previous structured compression rivals under multiple compression ratios. Our code will be released soon.

The collected data in recommender systems generally suffers selection bias. Considerable works are proposed to address selection bias induced by observed user and item features, but they fail when hidden features (e.g., user age or salary) that affect both user selection mechanism and feedback exist, which is called hidden confounding. To tackle this issue, methods based on sensitivity analysis and leveraging a few randomized controlled trial (RCT) data for model calibration are proposed. However, the former relies on strong assumptions of hidden confounding strength, whereas the latter relies on the expensive RCT data, thereby limiting their applicability in real-world scenarios. In this paper, we propose to employ heterogeneous observational data to address hidden confounding, wherein some data is subject to hidden confounding while the remaining is not. We argue that such setup is more aligned with practical scenarios, especially when some users do not have complete personal information (thus assumed with hidden confounding), while others do have (thus assumed without hidden confounding). To achieve unbiased learning, we propose a novel meta-learning based debiasing method called MetaDebias. This method explicitly models oracle error imputation and hidden confounding bias, and utilizes bi-level optimization for model training. Extensive experiments on three public datasets validate our method achieves state-of-the-art performance in the presence of hidden confounding, regardless of RCT data availability.

Abstract Retinal microaneurysm (MA) is a definite earliest clinical sigh of diabetic retinopathy (DR). Its automatic segmentation is key to realizing intelligent screening for early DR, which can significantly reduce the risk of visual impairment in patients. However, the minute scale and subtle contrast of MAs against the background pose challenges for segmentation. This paper focuses on automatic MA segmentation in fundus images. A novel pyramid feature fusion network (PFFNet) that progressively develops and fuses rich contextual information by integrating two pyramid modules is proposed. Multiple global pyramid scene parsing (GPSP) modules are introduced between the encoder and decoder to provide diverse global contextual information for the decoder through reconstructing skip connections. Additionally, a spatial scale‐aware pyramid (SSAP) module is introduced to dynamically fuse multi‐scale contextual information. This rich contextual information will help to identify MAs from low‐contrast background. Furthermore, to mitigate issue related to category imbalance, a combo loss function is introduced. Finally, to validate the effectiveness of the proposed method, experiments are conducted on two publicly available datasets, IDRiD and DDR, and PFFNet is compared with several state‐of‐the‐art models. The experimental results demonstrate the superiority of our PFFNet in the MA segmentation task.

Stable operation of IoT systems in extreme environments is critical for infrastructures, including energy, aerospace, and healthcare. But resource-constrained devices are vulnerable to malware exploiting known weaknesses due to complex operating conditions and low-frequency device maintenance, and systems are at serious risk of failure or information leakage. However, automated security defense based on machine learning faces the challenges of low cross-architectural generalization and multidimensional data imbalance. We propose a many-objective-optimization-driven data balancing strategy for cross-architectural malware classification (MODSC) to address the above issues. MODSC constructs the optimization problem model for data balancing strategy search based on data set information, which focuses on rebalancing the data space in different dimensions, including category distribution and architectural distribution. The many-objective evolutionary algorithm (MaOEA-PBF), guided by the performance balance function, is then designed to solve the above model. The MODSC framework was tested on a group of IoT malware data sets with stepped imbalance rates containing six common architectures. The experimental results show that MODSC can both steadily and effectively improve cross-architectural generalization while maintaining a high level of confidence compared to popular data processing methods.

Synthetic aperture radar (SAR) image classification has proven its significant importance in automatic remote sensing. However, current methods demand a large volume of training data to ensure satisfactory generalization capability. Given the difficulty in obtaining sufficient labeled samples, semi-supervised learning for SAR image classification becomes extremely important. However, existing studies are hindered by sample relationship modeling and single sample descriptions, leading to limited performance. To address this issue, we propose an innovative approach: multiview subspace tensor self-representation learning with label propagation for SAR image classification. Initially, our method extracts global sample relationship matrices of SAR samples using subspace self-representation learning with affine and nonnegative constraints. To enhance the single sample feature description, we construct multiview tensor learning by stacking the subspace representation matrices of different SAR view features. Finally, the SAR image multiview subspace self-representation matrix is treated as the probability indication matrix for classification. The experiments on MSTAR using extreme 10% labeled samples have shown that the proposed method yields performance boosts of 22.3% and 12.2% to the state-of-the-art method under two rigorous evaluation settings, respectively. The remarkably superior experimental results effectively validate the effectiveness of our proposals.

Information Bottleneck (IB) provides an information-theoretic principle for multi-view learning by revealing the various components contained in each viewpoint. This highlights the necessity to capture their distinct roles to achieve view-invariance and predictive representations but remains under-explored due to the technical intractability of modeling and organizing innumerable mutual information (MI) terms. Recent studies show that sufficiency and consistency play such key roles in multi-view representation learning, and could be preserved via a variational distillation framework. But when it generalizes to arbitrary viewpoints, such strategy fails as the mutual information terms of consistency become complicated. This paper presents Multi-View Variational Distillation (MV$^{2}$D), tackling the above limitations for generalized multi-view learning. Uniquely, MV$^{2}$D can recognize useful consistent information and prioritize diverse components by their generalization ability. This guides an analytical and scalable solution to achieving both sufficiency and consistency. Additionally, by rigorously reformulating the IB objective, MV$^{2}$D tackles the difficulties in MI optimization and fully realizes the theoretical advantages of the information bottleneck principle. We extensively evaluate our model on diverse tasks to verify its effectiveness, where the considerable gains provide key insights into achieving generalized multi-view representations under a rigorous information-theoretic principle.

Extremely large-scale array (XL-array) and Terahertz (THz) band have emerged as key research areas in the sixth generation (6G) network. As such, the near-field communication becomes more important since users are more likely to be located in the near-field. Different from their far-field counterparts, the near-field focusing beams utilize additional distance information to focus beam energy at specific spatial-locations. In this letter, we consider a uniform circular array (UCA) system and propose a fast distance sampling method for UCA and design its codebook. Specifically, we propose the non-uniform distance sampling and codebook for UCA by utilizing the zero-order Bessel function, and taking into account the effect of the distance information on the correlation between the near-field beam vectors of UCA. Based on the proposed non-uniform distance sampling and codebook, a two-stage searching scheme for three-dimensional (3D) beam focusing is designed. Simulation results verify that the designed beam focusing scheme can achieve comparable accuracy and rate performance as compared to the 3D exhaustive search.

Epilepsy, one of the world's most common neurological diseases, impacts over 1% of the global population. Accurate early prediction of epileptic seizure has a great influence on epileptic patients' lives and attracted extensive attention. However, existing methods do not fully consider the complexity of multi-channel electroencephalogram (EEG) signal, which is the most common measurement for epileptic seizures. In this letter, we propose a Dynamic Functional Connectivity neural Network (DynFCNet) for epileptic seizure prediction. The proposed DynFCNet can discover dynamic brain functional connections and generate dynamic functional connectivity graphs, as well as extract non-Euclidean features from multi-channel EEG signals by Graph Convolutional Network (GCN). To take Euclidean features into consideration, Convolutional Neural Network (CNN) as one of the branches is also employed. Further, we incorporated both intra-group loss and inter-group loss to enhance our DynFCNet. Extensive experiments were implemented on a public multi-channel EEG dataset (CHB-MIT). The results confirm that our proposal outperforms the other competitors

Multi-view clustering has become a research hotspot in recent decades because of its effectiveness in heterogeneous data fusion. Although a large number of related studies have been developed one after another, most of them usually only concern with the characteristics of the data themselves and overlook the inherent connection among samples, hindering them from exploring structural knowledge of graph space. Moreover, many current works tend to highlight the compactness of one cluster without taking the differences between clusters into account. To track these two drawbacks, in this paper, we propose a graph structure aware contrastive multi-view clustering (namely, GCMC) approach. Specifically, we incorporate the well-designed graph autoencoder with conventional multi-layer perception autoencoder to extract the structural and high-level representation of multi-view data, so that the underlying correlation of samples can be effectively squeezed for model learning. Then the contrastive learning paradigm is performed on multiple pseudo-label distributions to ensure that the positive pairs of pseudo-label representations share the complementarity across views while the divergence between negative pairs is sufficiently large. This makes each semantic cluster more discriminative, i.e., jointly satisfying intra-cluster compactness and inter-cluster exclusiveness. Through comprehensive experiments on eight widely-known datasets, we prove that the proposed approach can perform better than the state-of-the-art opponents.

The proper use of medical personal protective equipment (MPPE) is critical for frontline healthcare workers (HCWs) to handle highly contagious diseases. Due to the complexity of PPE donning and doffing protocols, public health organizations typically recommend having trained observers monitor the entire PPE donning and doffing process, preventing self-contamination and transmission. However, the high costs of manual monitoring impede the implementation of this practice, which makes AI-assisted PPE monitoring highly valuable. Some studies have applied computer vision techniques to PPE monitoring, but they have only focused on limited integrity checks at donning completion, which is unable to provide real-time warnings for abnormal actions during the doffing process. Furthermore, model practicality and user-friendliness are constrained by the lack of explainability. To address this, we propose an explainable and fine-grained dataset for MPPE doffing monitoring called the XFMP dataset. The dataset contains 3596 expert-annotated samples over three sub-tasks: doffing stage classification (DSC), abnormal action recognition (AAR), and critical region localization (CRL). Accordingly, we introduce multi-dimensional evaluation metrics for XFMP and a multitask human behavior semantic attention network (MHBSAN). Experiments demonstrate that MHBSAN outperforms alternative approaches, achieving 0.968/0.855 accuracy for stage/action classification and 0.791 Top-1 [email protected] for CRL sub-task. Moreover, it demonstrates exceptional adaptability across different healthcare environments. Ablation studies and case analyses further validate the contributions and efficacy of the proposed model regarding classification and explainability.

Graph neural networks (GNNs) have achieved considerable success in dealing with graph-structured data by the message-passing mechanism. Actually, this mechanism relies on a fundamental assumption that the graph structure along which information propagates is perfect. However, the real-world graphs are inevitably incomplete or noisy, which violates the assumption, thus resulting in limited performance. Therefore, optimizing graph structure for GNNs is indispensable and important. Although current semi-supervised graph structure learning (GSL) methods have achieved a promising performance, the potential of labels and prior graph structure has not been fully exploited yet. Inspired by this, we examine GSL with dual reinforcement of label and prior structure in this article. Specifically, to enhance label utilization, we first propose to construct the prior label-constrained matrices to refine the graph structure by identifying label consistency. Second, to adequately leverage the prior structure to guide GSL, we develop spectral contrastive learning that extracts global properties embedded in the prior graph structure. Moreover, contrastive fusion with prior spatial structure is further adopted, which promotes the learned structure to integrate local spatial information from the prior graph. To extensively evaluate our proposal, we perform sufficient experiments on seven benchmark datasets, where experimental results confirm the effectiveness of our method and the rationality of the learned structure from various aspects.

Ship detection in high-resolution optical remote sensing images (ORSI) is an important yet challenging task with extensive applications, such as maritime security and resource conservation. In recent years, bolstered by deep learning, ship detection has also grown by leaps and bounds. Nevertheless, existing methods still suffer from two challenging issues: 1) imprecise localization for low discriminative ships under the complicated background and 2) missed detections for small ships. To solve the above issues, we propose a novel ship detection method equipped with a saliency-guided feature fusion network (SGFFN) and a dynamic IoU-adaptive strategy (DIAS). SGFFN is designed based on a top-down feature pyramid network to introduce saliency information into the ship detection network and optimize the saliency-aware features. It comprises two components: the resolution-matching saliency supervision (RMS) network and the cross-stage saliency integration network (CSIN). RMS is a bimatching mechanism that adopts diverse prediction structures for the saliency maps with different scales, such that the finer saliency-aware features could be obtained. CSIN is a cross-stage cross-channel integration module that is designed to fuse saliency-aware features with low-level features. Furthermore, a customized training strategy for small ships, i.e., DIAS, is devised to assign appropriate intersection over union (IoU) thresholds for anchors around the small ships during the training phase. Experimental results on two datasets demonstrate that our proposed method achieves state-of-the-art performance.

Survival analysis is employed to analyze the time before the event of interest occurs, which is broadly applied in many fields. The existence of censored data with incomplete supervision information about survival outcomes is one key challenge in survival analysis tasks. Although some progress has been made on this issue recently, the present methods generally treat the instances as separate ones while ignoring their potential correlations, thus rendering unsatisfactory performance. In this study, we propose a novel Deep Survival Analysis model with latent Clustering and Contrastive learning (DSACC). Specifically, we jointly optimize representation learning, latent clustering and survival prediction in a unified framework. In this way, the clusters distribution structure in latent representation space is revealed, and meanwhile the structure of the clusters is well incorporated to improve the ability of survival prediction. Besides, by virtue of the learned clusters, we further propose a contrastive loss function, where the uncensored data in each cluster are set as anchors, and the censored data are treated as positive/negative sample pairs according to whether they belong to the same cluster or not. This design enables the censored data to make full use of the supervision information of the uncensored samples. Through extensive experiments on four popular clinical datasets, we demonstrate that our proposed DSACC achieves advanced performance in terms of both C-index (0.6722, 0.6793, 0.6350, and 0.7943) and Integrated Brier Score (IBS) (0.1616, 0.1826, 0.2028, and 0.1120).

Multi-layer networks treat various types of interactions at each level to model complex systems in nature and society, and clustering of them is of great significance for revealing mechanisms of systems. Vast majority of current algorithms focus on identifying the common communities in clear multi-layer networks, and few attempt has been devoted to the detection of layer-specific communities in noised ones. To address these issues, a joint learning algorithm withGraphDenoising andStructureLearning (calledGDSL) for the detection of layer-specific communities in noised multi-layer networks is proposed, which simultaneously integrates graph denoising, structure learning, and module detection. To remove noise of networks, GDSL re-constructs affinity graphs for the original ones by preserving community structure. To enhance robustness and discriminative of features, GDSL explores the relations of features among various layers with the Hilbert-Schmidt Independence Criterion and structure learning. Finally, GDSL joins all these procedures with an objective function, and deduces optimization rules. The results show that GDSL not only significantly outperforms baselines but also enhances the robustness of the algorithm, providing an effective model for community detection in noised multi-layer networks.

Temporal link prediction on dynamic graphs has attracted considerable attention. Most methods focus on the graph at each timestamp and extract features for prediction. As graphs are directly compressed into feature matrices, the important latent information at each timestamp has not been well revealed. Eventually, the acquisition of dynamic evolution-related patterns is rendered inadequately. In this paper, inspired by the process of Super-Resolution (SR), a novel deep generative model SRG (Super Resolution Graph) is proposed. We innovatively introduce the concepts of the Low-Resolution (LR) graph, which is a single adjacent matrix at a timestamp, and the High-Resolution (HR) graph, which includes the link status of surrounding snapshots. Specifically, two major aspects are considered regarding the construction of the HR graph. For edges, we endeavor to obtain an extensive information transmission description that affects the current link status. For nodes, similar to the SR process, the neighbor relationship among nodes is maintained. In this form, we could predict the link status from a new perspective: Under the supervision of the graph moving average strategy, the conditional normalizing flow effectively realizes the transformation between LR and HR graphs. Extensive experiments on six real-world datasets from different applications demonstrate the effectiveness of our proposal.

Multiview clustering has become a research hotspot in recent years due to its excellent capability of heterogeneous data fusion. Although a great deal of related works has appeared one after another, most of them generally overlook the potentials of prior knowledge utilization and progressive sample learning, resulting in unsatisfactory clustering performance in real-world applications. To deal with the aforementioned drawbacks, in this article, we propose a semisupervised progressive representation learning approach for deep multiview clustering (namely, SPDMC). Specifically, to make full use of the discriminative information contained in prior knowledge, we design a flexible and unified regularization, which models the sample pairwise relationship by enforcing the learned view-specific representation of must-link (ML) samples (cannot-link (CL) samples) to be similar (dissimilar) with cosine similarity. Moreover, we introduce the self-paced learning (SPL) paradigm and take good care of two characteristics in terms of both complexity and diversity when progressively learning multiview representations, such that the complementarity across multiple views can be squeezed thoroughly. Through comprehensive experiments on eight widely used image datasets, we prove that the proposed approach can perform better than the state-of-the-art opponents.

Biomedical entity linking is an essential task in biomedical text processing, which aims to map entity mentions in biomedical text to standard terms in a given knowledge base.However, this task is challenging due to the rarity of many biomedical entities in real-world scenarios, which leads to a lack of annotated data for them.Limited by understanding these unseen entities, traditional biomedical entity linking models suffer from multiple types of linking errors.In this paper, we propose a novel latent feature generation framework BioFEG to address these challenges.Specifically, our BioFEG leverages domain knowledge to train a generative adversarial network, which generates latent semantic features of corresponding mentions for unseen entities.Utilizing these features, we fine-tune our entity encoder to capture fine-grained coherence information of unseen entities and better understand them.This allows models to make linking decisions more accurately, particularly for ambiguous mentions involving rare entities.Extensive experiments on the two benchmark datasets demonstrate the superiority of our proposed method.

Summary With the number of services expanding in the Internet of Things (IoT), the limited resources of user terminals are insufficient to satisfy the computation needs of all running services. Therefore, we design a collaborative computation‐offloading model (CCOM) composed of multiple servers and task offloading modes to solve the problem by offloading tasks from resource‐constrained terminals to other computing entities, which achieves the following four objectives: model execution time minimization, task execution time minimization, energy consumption minimization, and most efficient device workload. And the global evaluation strategy based on angle and distance is proposed to address the individual selection problems caused by the overly localized Pareto dominance relationship and objective conflicts in the many‐objective evolutionary algorithms. In simulations, the strategy achieves the best Inverted Generation Distance (IGD) performance on 22 benchmark test problems based on Wilcoxon's rank sum statistical test and improves performance in the four objectives above by 18%, 31%, 20%, and 42%, respectively. Finally, we think that the strategy can provide adequate offloading performance for decision‐makers.

Low-rank self-representation based subspace learning has confirmed its great effectiveness in a broad range of applications. Nevertheless, existing studies mainly focus on exploring the global linear subspace structure, and cannot commendably handle the case where the samples approximately (i.e., the samples contain data errors) lie in several more general affine subspaces. To overcome this drawback, in this paper, we innovatively propose to introduce affine and nonnegative constraints into low-rank self-representation learning. While simple enough, we provide their underlying theoretical insight from a geometric perspective. The union of two constraints geometrically restricts each sample to be expressed as a convex combination of other samples in the same subspace. In this way, when exploring the global affine subspace structure, we can also consider the specific local distribution of data in each subspace. To comprehensively demonstrate the benefits of introducing two constraints, we instantiate three low-rank self-representation methods ranging from single-view low-rank matrix learning to multi-view low-rank tensor learning. We carefully design the solution algorithms to efficiently optimize the proposed three approaches. Extensive experiments are conducted on three typical tasks, including single-view subspace clustering, multi-view subspace clustering, and multi-view semi-supervised classification. The notably superior experimental results powerfully verify the effectiveness of our proposals.

Advances in single-cell biotechnologies have generated the single-cell RNA sequencing (scRNA-seq) of gene expression profiles at cell levels, providing an opportunity to study cellular distribution. Although significant efforts developed in their analysis, many problems remain in studying cell types distribution because of the heterogeneity, high dimensionality, and noise of scRNA-seq. In this study, a multi-view clustering with graph learning algorithm (MCGL) for scRNA-seq data is proposed, which consists of multi-view learning, graph learning, and cell type clustering. In order to avoid a single feature space of scRNA-seq being inadequate to comprehensively characterize the functions of cells, MCGL constructs the multiple feature spaces and utilizes multi-view learning to comprehensively characterize scRNA-seq data from different perspectives. MCGL adaptively learns the similarity graphs of cells that overcome the dependence on fixed similarity, transforming scRNA-seq analysis into the analysis of multi-view clustering. MCGL decomposes the networks of cells into view-specific and common networks in multi-view learning, which better characterizes the topological relationship of cells. MCGL simultaneously utilizes multiple types of cell-cell networks and fully exploits the connection relationship between cells through the complementarity between networks to improve clustering performance. The graph learning, graph factorization, and cell-type clustering processes are accomplished simultaneously under one optimization framework. The performance of the MCGL algorithm is validated with ten scRNA-seq datasets from different scales, and experimental results imply that the proposed algorithm significantly outperforms fourteen state-of-the-art scRNA-seq algorithms.

As one of the learning ways for inducing efficient image compact representation, graph embedding (GE) based manifold learning has been widely developed over the last two decades. Good graph embedding depends on the construction of graphs concerning intra-class compactness and inter-class separability, which are crucial indicators of the effectiveness of a model in generating discriminative features. Unsupervised approaches are designed to reveal the data structure information from a local or global perspective, but the resulting compact representation often has poorly inter-class margins due to the lack of label information. Moreover, supervised techniques only consider enhancing the adjacency affinity within classes, but exclude the affinity of different classes, resulting in inadequate capture of marginal structures between different class distributions. To overcome these issues, we propose a learning framework that implements Class-Oriented Self-Learning Graph Embedding (COSLGE), in which we achieve a flexible low-dimensional compact representation by imposing an adaptive graph learning process across the entire data while examining the inter-class separability of low-dimensional embedding by jointly learning a linear classifier. Besides, our framework can be easily extended to semi-supervised scenarios. Extensive experiments on several widely-used benchmark databases demonstrate the effectiveness of the proposed method in comparison to some state-of-the-art approaches.

Aiming at the large distortion and low tampering localization accuracy of the existing semi-fragile reversible watermarking for 3D mesh models, a novel semi-fragile reversible watermarking for 3D models using spherical crown volume division is proposed. The crown volume of a sphere is divided to reduce the embedding distortion. The possible geometric and topological transformations are separately considered in the watermark generation, and the vertices of the one-ring neighbourhood are grouped to improve the tampering localization accuracy. Experimental results show that the proposed scheme can achieve better localization accuracy and lower embedding distortion than some state-of-the-art algorithms. It has good potential for the applications in integrity authentication for 3D mesh models.

The rapid progress of artificial intelligence expands its wide applicability in Internet of Things (IoT). Meanwhile, data insufficient and data source privacy are key supply chain challenges facing IoT especially in the healthcare industry. To address this problem in healthcare IoT, in this article, we propose a skin cancer detection model based on federated learning integrated with deep generation model. First, we employ dual generative adversarial networks to address the problem of insufficient data. In addition, to improve the quality of generated images, we synchronously optimize the sharpness of images, Frechet inception distance, image diversity, and loss using knee point-driven evolutionary algorithm (KnEA). Then, we protect patient information privacy by training federated skin cancer framework. Finally, we employ the ISIC 2018 dataset to test the performance of the proposed training model under different situations, including using identically distributed data, nonidentically distributed data, a sparse convolutional neural network, and a fully connected convolutional neural network. The experiment results demonstrate that the accuracy and area under the curve reach 91% and 88%, respectively. This model can help resolve problems of insufficient data in smart medicine of IoT and protect the privacy of user data while also providing an excellent detection rate.

Domain generalizable person re-identification (DG ReID) is a challenging problem, because the trained model is often not generalizable to unseen target domains with different distribution from the source training domains. Data augmentation has been verified to be beneficial for better exploiting the source data to improve the model generalization. However, existing approaches primarily rely on pixel-level image generation that requires designing and training an extra generation network, which is extremely complex and provides limited diversity of augmented data. In this paper, we propose a simple yet effective feature based augmentation technique, named Style-uncertainty Augmentation (SuA). The main idea of SuA is to randomize the style of training data by perturbing the instance style with Gaussian noise during training process to increase the training domain diversity. And to better generalize knowledge across these augmented domains, we propose a progressive learning to learn strategy named Self-paced Meta Learning (SpML) that extends the conventional one-stage meta learning to multi-stage training process. The rationality is to gradually improve the model generalization ability to unseen target domains by simulating the mechanism of human learning. Furthermore, conventional person Re-ID loss functions are unable to leverage the valuable domain information to improve the model generalization. So we further propose a distance-graph alignment loss that aligns the feature relationship distribution among domains to facilitate the network to explore domain-invariant representations of images. Extensive experiments on four large-scale benchmarks demonstrate that our SuA-SpML achieves state-of-the-art generalization to unseen domains for person ReID.

We propose a Meta Learning on Randomized Transformations (MLRT) to learn domain invariant object detectors. Domain generalization is a problem about learning an invariant model from multiple source domains which can generalize well on unseen target domains. This problem is overlooked in object detection field, which is formally named as domain generalizable object detection (DGOD). Moreover, existing domain generalization methods have the problem of domain bias so that they can easily overfit to some specific domain (e.g., source domain). In order to alleviate the domain bias, in MLRT model, a novel randomized spectrum transformation (RST) module is proposed to increase the diversity of source domains. Specifically, RST randomizes the domain specific information of images in frequency-space, which can transform single or multiple source domains into various new domains. Besides, we observe a prior that the gradient imbalance degree among domains can also reflect the domain bias. Therefore, we further propose to alleviate the domain bias from the perspective of gradient balancing, and a novel gradient weighting (GW) module is proposed to balance the gradients over all domains via a hand-crafted weight. Finally we embed our RST and GW into a general meta learning framework and the proposed MLRT model is formalized for DGOD task. Extensive experiments are conducted on six benchmarks, and our method achieves the SOTA performance.

This study presents three deidentified large medical text datasets, named DISCHARGE, ECHO and RADIOLOGY, which contain 50 K, 16 K and 378 K pairs of report and summary that are derived from MIMIC-III, respectively. We implement convincing baselines of automated abstractive summarization on the created datasets with pre-trained encoder-decoder language models, including BERT2BERT, BERTShare, RoBERTaShare, Pegasus, ProphetNet, T5-large, BART and GSUM. Further, based on the BART model, we leverage the sampled summaries from the training set as prior knowledge guidance, for encoding additional contextual representations of the guidance with the encoder and enhancing the decoding representations in the decoder. The experimental results confirm the improvement of ROUGE scores and BERTScore made by the proposed method.

Advances in single-cell biotechnologies simultaneously generate the transcriptomic and epigenomic profiles at cell levels, providing an opportunity for investigating cell fates. Although great efforts have been devoted to either of them, the integrative analysis of single-cell multi-omics data is really limited because of the heterogeneity, noises and sparsity of single-cell profiles. In this study, a network-based integrative clustering algorithm (aka NIC) is present for the identification of cell types by fusing the parallel single-cell transcriptomic (scRNA-seq) and epigenomic profiles (scATAC-seq or DNA methylation). To avoid heterogeneity of multi-omics data, NIC automatically learns the cell-cell similarity graphs, which transforms the fusion of multi-omics data into the analysis of multiple networks. Then, NIC employs joint non-negative matrix factorization to learn the shared features of cells by exploiting the structure of learned cell-cell similarity networks, providing a better way to characterize the features of cells. The graph learning and integrative analysis procedures are jointly formulated as an optimization problem, and then the update rules are derived. Thirteen single-cell multi-omics datasets from various tissues and organisms are adopted to validate the performance of NIC, and the experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art methods in terms of various measurements. The proposed algorithm provides an effective strategy for the integrative analysis of single-cell multi-omics data (The software is coded using Matlab, and is freely available for academic https://github.com/xkmaxidian/NIC ).

Classification of nonprecipitation echoes of radar is an inevitable step in radar-based precipitation estimation. Among nonprecipitation echoes, clear air echoes are specifically difficult to distinguish for their similarity to precipitation echoes. This letter aims to conduct a pixelwise classification of clear air echoes for image sequences of the radar reflectivity. We propose the Static and Motion streams Network (SMNet) to simultaneously utilize the static and motion features. SMNet realizes capturing the spatiotemporal characteristics while maintaining the details of the current frame via a fusion structure and a novel training method. For feature fusion, the static and motion streams are concatenated. Then, for model training, we adopt a dynamic weight assignment strategy to further extract rich information. Finally, we validate our method on an S-band single-polarization radar in Beijing, China, from May to September 2018. The results demonstrate that the overall performance of SMNet is superior to other competitors.

Multi-view data effectively model and characterize the underlying complex systems, and multi-view clustering is of great significance for revealing the mechanisms of systems, which groups objects into different clusters with high intra-cluster and low inter-cluster similarity for all views. Current algorithms are criticized for undesirable performance because they solely focus on either the shared features or correlation of objects, failing to address the heterogeneity and structural constraint of various views. To overcome these problems, a novelMulti-viewClustering withSelf-representation andStructuralConstraint (MCSSC) is proposed, which is a network-based method by fusing matrix factorization and low-rank representation of various views. Specifically, to remove heterogeneity of multi-view data, a network is constructed for each view, which casts the multi-view clustering into the multi-layer networks clustering problem. To extract the shared features of multiple views, MCSSC factorizes matrices associated with networks by projecting them into a common space and jointly learns an affinity graph for objects in multiple views with self-representation. To facilitate the clustering, the structural constraint is imposed on the affinity graph, where the clusters are identified. Extensive experiments demonstrate that MCSSC significantly outperforms the state-of-the-art in terms of accuracy, implying that the superiority of the proposed method.

With the dramatic increase of dimensions in the data representation, extracting latent low-dimensional features becomes of the utmost importance for efficient classification. Aiming at the problems of weakly discriminating marginal representation and difficulty in revealing the data manifold structure in most of the existing linear discriminant methods, we propose a more powerful discriminant feature extraction framework, namely, joint sparse locality-aware regression (JSLAR). In our model, we formulate a new strategy induced by the nonsquared$L_{2}$norm for enhancing the local intraclass compactness of the data manifold, which can achieve the joint learning of the locality-aware graph structure and the desirable projection matrix. Besides, we formulate a weighted retargeted regression to perform the marginal representation learning adaptively instead of using the general average interclass margin. To alleviate the disturbance of outliers and prevent overfitting, we measure the regression term and locality-aware term together with the regularization term by forcing the row sparsity with the joint$L_{2,1}$norms. Then, we derive an effective iterative algorithm for solving the proposed model. The experimental results over a range of benchmark databases demonstrate that the proposed JSLAR outperforms some state-of-the-art approaches.

Multiview subspace clustering (MSC) has attracted growing attention due to the extensive value in various applications, such as natural language processing, face recognition, and time-series analysis. In this article, we are devoted to address two crucial issues in MSC: 1) high computational cost and 2) cumbersome multistage clustering. Existing MSC approaches, including tensor singular value decomposition (t-SVD)-MSC that has achieved promising performance, generally utilize the dataset itself as the dictionary and regard representation learning and clustering process as two separate parts, thus leading to the high computational overhead and unsatisfactory clustering performance. To remedy these two issues, we propose a novel MSC model called joint skinny tensor learning and latent clustering (JSTC), which can learn high-order skinny tensor representations and corresponding latent clustering assignments simultaneously. Through such a joint optimization strategy, the multiview complementary information and latent clustering structure can be exploited thoroughly to improve the clustering performance. An alternating direction minimization algorithm, which owns low computational complexity and can be run in parallel when solving several key subproblems, is carefully designed to optimize the JSTC model. Such a nice property makes our JSTC an appealing solution for large-scale MSC problems. We conduct extensive experiments on ten popular datasets and compare our JSTC with 12 competitors. Five commonly used metrics, including four external measures (NMI, ACC, F-score, and RI) and one internal metric (SI), are adopted to evaluate the clustering quality. The experimental results with the Wilcoxon statistical test demonstrate the superiority of the proposed method in both clustering performance and operational efficiency.

Diabetic retinopathy (DR) grading from fundus images has attracted increasing interest in both academic and industrial communities. Most convolutional neural network-based algorithms treat DR grading as a classification task via image-level annotations. However, these algorithms have not fully explored the valuable information in the DR-related lesions. In this article, we present a robust framework, which collaboratively utilizes patch-level and image-level annotations, for DR severity grading. By an end-to-end optimization, this framework can bidirectionally exchange the fine-grained lesion and image-level grade information. As a result, it exploits more discriminative features for DR grading. The proposed framework shows better performance than the recent state-of-the-art algorithms and three clinical ophthalmologists with over nine years of experience. By testing on datasets of different distributions (such as label and camera), we prove that our algorithm is robust when facing image quality and distribution variations that commonly exist in real-world practice. We inspect the proposed framework through extensive ablation studies to indicate the effectiveness and necessity of each motivation. The code and some valuable annotations are now publicly available.

Ship detection is a crucial but challenging task in optical remote sensing images. Recently, thanks to the emergence of deep neural networks, significant progress has been made in ship detection. However, there are still two significant issues that must be addressed: 1) The high-resolution optical images may confuse the background with the ship, leading to more false alarms during detection; 2) The detector receives fewer positive samples due to the sparse and uneven distribution of ships in the optical remote sensing images. In this paper, we innovatively propose employing the saliency information to aid the ship detection task to tackle these two issues. To achieve this goal, we devise two novel modules, Feature-Enhanced Structure (FES) and Saliency Prediction Branch (SPB), to boost the capacity of ship detection in complex environments, and propose a new sampling strategy named Salient Screening Mechanism (SSM) to increase the number of positive samples. More specifically, SSM is adopted during the training phase to mine more positive samples from the ignored set. Then, in an end-to-end learning fashion, a neural network that incorporates our carefully designed FES and SPB is trained to gain more discriminative information for distinguishing the foreground and the background. To evaluate the effectiveness of our proposal, two new datasets HRSC-SO and DOTA-isaid-ship are constructed, which possesses the annotation information for both object detection and saliency detection. We conduct extensive experiments on the constructed dataset, and the results demonstrate that our method outperforms the previous state-of-the-art approaches.

Short-term quantitative precipitation forecasting (SQPF) using weather radar is an important but challenging problem as one must cope with inherent nonlinearity and spatiotemporal correlation in the data. In this article, we propose a novel deep learning model, named Inductive spatiotemporal Graph Convolutional Networks (InstGCNs), to overcome these issues in SQPF. The proposed InstGCN can learn a nonlinear mapping from historical radar reflectivity to future rainfall amounts and extract informative spatiotemporal representations simultaneously. Specifically, we first provide a formal definition for formulating the SQPF problem from a graph perspective. Then, based on radar reflectivity and rain gauge observation, we propose a novel graph construction approach that utilizes a special elliptic structure to model the spatial dependence of precipitation areas. In addition, a new Node level Differential Block (Node-DB) is introduced to tackle the nonstationary temporal dependence. To execute inductive graph learning for unseen nodes, we design to decompose a whole graph into subgraphs. We conduct extensive experiments on three real-world datasets in East China and a public weather radar dataset in the southeastern parts of France. The experimental results confirm the advantages of InstGCN compared with several state of the arts.

Multi-view subspace clustering is an effective method to partition data into their corresponding categories. Nevertheless, existing multi-view subspace clustering approaches generally operate in a purely unsupervised manner, while ignoring the valuable weakly supervised information that can be readily obtained in many practical applications. In this paper, we consider the weakly supervised form of sample pair constraints, and devote to promoting the performance of multi-view subspace clustering with the aid of such prior knowledge. To achieve this goal, inspired by the intrinsic block diagonal structure of ideal low-rank representation (LRR), we propose a novel regularization to integrate must-link, cannot-link and normalization constraints into a unified formulation. The proposed regularization can be regarded as a general description for sample pairwise constraints, and thus provides a flexible framework for multi-view semi-supervised subspace clustering task. Furthermore, we devise a contrained tensor representation learning (CTRL) model that takes advantage of our proposed regularization to facilitate the learning of the desired representation tensor. An efficient optimization algorithm based on alternating direction minimization strategy is carefully designed to solve the proposed CTRL model. Extensive experiments on eight challenging real-world datasets are conducted, and the results validate the effectiveness of our designed pairwise constraints regularization, as well as the superiority of the proposed CTRL model.

Aiming at the problem that it is easily trapped into a local optimum when applying steepest gradient descent method to train feedforward neural network, in this paper we propose an algorithm based on non-monotone conjugate gradient to optimize the training process of feedforward neural network that used in the multiple classification task. More specifically, the proposed method combines the conjugate gradient descent method and the non-monotone linear search technique, and makes full use of the information of loss function and its gradients, resulting in a faster convergence rate without increasing the memory consumption than the traditional gradient descent method. Extensive experiments carried out on VCI database indicate that the proposed algorithm possesses a good generalization ability and works well in the multi-classification problem measured by accuracy and Macro-Fl score.

The Internet-of-Things (IoT) technology is widely used in various fields. In the Earth observation system, hyperspectral images (HSIs) are acquired by hyperspectral sensors and always transmitted to the cloud for analysis. In order to reduce cost and reply promptly, we deploy artificial intelligence (AI) models for data analysis on edge servers. Subspace clustering, the core of the AI model, is employed to analyze high-dimensional image data such as HSIs. However, most traditional subspace clustering algorithms construct a single model, which can be affected by noise more easily. It hardly balances the sparsity and connectivity of the representation coefficient matrix. Therefore, we proposed a postprocess strategy of subspace clustering for taking account of sparsity and connectivity. First, we define close neighbors as having more common neighbors and higher coefficients neighbors, where the close neighbors are selected according to the nondominated sorting algorithm. Second, the coefficients between the sample and close neighbors are reserved, incorrect, or useless connections are pruned. Then, the postprocess strategy can reserve the intrasubspace connection and prune the intersubspace connection. In experiments, we verified the universality and effectiveness of postprocessing strategies in the traditional image recognition field and IoT field, respectively. The experiment results demonstrate that the proposed strategy can process noise data in the IoT to improve clustering accuracy.

Accurate and high-resolution quantitative precipitation estimation (QPE) plays a crucial role in meteorology and hydrology. However, for acquiring a more accurate QPE, how to depict the complex nonlinear relationship between the radar reflectivity and the true rain rates, as well as adaptively explore the spatial dependencies of precipitation, remains extremely challenging. In this letter, we propose to incorporate the merits of graph convolutional regression networks (GCRNs) and address the aforementioned issues simultaneously in the GCRNs framework. Furthermore, in order to tolerate the variabilities of spatial correlation in the practical precipitation, we expand GCRNs with a multiconvolutional mechanism between the center node and its neighbor rain gauges. Thus, the ability to capture more complicated spatial characteristics of precipitation can be enhanced, and the phenomenon of overwhelming by the neighbor nodes can be released. Extensive experiments were implemented on 12 rainfall processes in Hangzhou, China, 2015. The experimental results confirm that our proposal consistently outperforms the state-of-the-art QPE models.

Domain adaptation in person re-identification (re-ID) has always been challenging, especially for the lack of supervision information on the target domain. Existing methods generally introduced extra supervision by adversarial learning techniques, then added all the augmented data in the training process to optimize the re-ID model. However, the direct utilization of all the generated data not only increases additional computational cost but also ignores the potential correlation between the origin and generated data. In this article, we propose a novel dual-alignment learning framework (DAL) with camera-aware image generation to efficiently and effectively tackle this issue. Specifically, we propose a camera transfer matching module to generate additional training images with different camera styles, and construct the matching pairs with each containing a origin image and one corresponding camera transferred image. To strengthen the correlation of images for each matching pair, we align the pseudo-labels via clustering algorithm to reduce the pseudo-labels distribution discrepancy between the origin and generated images. Besides, to avoid model degeneration affected by some inaccurate pseudo-labels on unlabelled data, we maximize the mutual information to align the image feature representations of matching pair. The DAL allows us to decrease the camera variance and enhance the discrimination ability of re-ID model. Extensive experiments on three large-scale benchmarks demonstrate the superiority of DAL over state-of-the-art methods.

While the industrial Internet of Things (IIoT) can support efficient control of the physical world through large amounts of industrial data, data security has been a challenge due to various interconnections and accesses. Blockchain technology can support security and privacy preservation in IIoT data with its trusted and reliable security mechanism. Sharding technology can help improve the overall throughput and scalability of blockchain networks. However, the effectiveness of sharding is still challenging due to the uneven distribution of malicious nodes. By aiming to improve the performance of blockchain networks and reduce the possibility of malicious node aggregation, in this article, we propose a many-objective optimization algorithm based on the dynamic reward and penalty mechanism (MaOEA-DRP) to optimize the shard validation validity model. Then, an optimal blockchain sharding scheme is obtained. Compared with other state-of-the-art many-objective optimization algorithms, MaOEA-DRP performs better on the DTLZ test suite. The simulation results demonstrate that our proposed algorithm can significantly improve the throughput and validity of sharding for better security in the blockchain-enabled IIoT.

Time series clustering has attracted growing attention due to the abundant data accessible and extensive value in various applications. The unique characteristics of time series, including high-dimension, warping, and the integration of multiple elastic measures, pose challenges for the present clustering algorithms, most of which take into account only part of these difficulties. In this paper, we make an effort to simultaneously address all aforementioned issues in time series clustering under a unified multiple kernels clustering (MKC) framework. Specifically, we first implicitly map the raw time series space into multiple kernel spaces via elastic distance measure functions. In such high-dimensional spaces, we resort to the tensor constraint based self-representation subspace clustering approach, which involves the self-paced learning paradigm, to explore the essential low-dimensional structure of the data, as well as the high-order complementary information from different elastic kernels. The proposed approach can be extended to more challenging multivariate time series clustering scenario in a direct but elegant way. Extensive experiments on 85 univariate and 10 multivariate time series datasets demonstrate the significant superiority of the proposed approach beyond the baseline and several state-of-the-art MKC methods.

In this paper, a novelDeepMulti-viewJointClustering (DMJC) framework is proposed, where multiple deep embedded features, multi-view fusion mechanism, and clustering assignments can be learned simultaneously. Through the joint learning strategy, the clustering-friendly multi-view features and useful multi-view complementary information can be exploited effectively to improve the clustering performance. Under the proposed joint learning framework, we design two ingenious variants of deep multi-view joint clustering models, whose multi-view fusion is implemented by two kinds of simple yet effective schemes. The first model, called DMJC-S, performs multi-view fusion in an implicit way via a novel multi-view soft assignment distribution. The second model, termed DMJC-T, defines a novel multi-view auxiliary target distribution to conduct the multi-view fusion explicitly. Both DMJC-S and DMJC-T are optimized under a KL divergence objective. Experiments on eight challenging image datasets demonstrate the superiority of both DMJC-S and DMJC-T over single/multi-view baselines and the state-of-the-art multi-view clustering methods, which proves the effectiveness of the proposed DMJC framework. To the best of our knowledge, this is the first work to model the multi-view clustering in a deep joint framework, which will provide a meaningful thinking in unsupervised multi-view learning.

In this article, we propose a multiview self-representation model for nonlinear subspaces clustering. By assuming that the heterogeneous features lie within the union of multiple linear subspaces, the recent multiview subspace learning methods aim to capture the complementary and consensus from multiple views to boost the performance. However, in real-world applications, data feature usually resides in multiple nonlinear subspaces, leading to undesirable results. To this end, we propose a kernelized version of tensor-based multiview subspace clustering, which is referred to as Kt-SVD-MSC, to jointly learn self-representation coefficients in mapped high-dimensional spaces and multiple views correlation in unified tensor space. In view-specific feature space, a kernel-induced mapping is introduced for each view to ensure the separability of self-representation coefficients. In unified tensor space, a new kind of tensor low-rank regularizer is employed on the rotated self-representation coefficient tensor to preserve the global consistency across different views. We also derive an algorithm to efficiently solve the optimization problem with all the subproblems having closed-form solutions. Furthermore, by incorporating the nonnegative and sparsity constraints, the proposed method can be easily extended to a useful variant, meaning that several useful variants can be easily constructed in a similar way. Extensive experiments of the proposed method are tested on eight challenging data sets, in which a significant (even a breakthrough) advance over state-of-the-art multiview clustering is achieved.

In meteorology, ensemble forecasting aims to post-process an ensemble of multiple members’ forecasts and make better weather predictions. While multiple individual forecasts are generated to represent the uncertain weather system, the performance of ensemble forecasting is unsatisfactory. In this p aper we conduct data analysis based on the expertise of human forecasters and introduce a machine learning method for ensemble forecasting. The proposed method, Label Distribution Learning with Climate Probability (LDLCP), can improve the accuracy of both deterministic forecasting and probabilistic forecasting. The LDLCP method utilizes the relevant variables of previous forecasts to construct the feature matrix and applies label distribution learning (LDL) to adjust the probability distribution of ensemble forecast. Our proposal is novel in its specialized target function and appropriate conditional probability function for the ensemble forecasting task, which can optimize the forecasts to be consistent with local climate. Experimental testing is performed on both artificial data and the data set for ensemble forecasting of precipitation in East China from August to November, 2017. Experimental results show that, compared with a baseline method and two state-of-the-art machine learning methods, LDLCP shows significantly better performance on measures of RMSE and average continuous ranked probability score.

While quantitative precipitation estimation (QPE) using weather radar is widely adopted in operation, precipitation data sets are often highly imbalanced. In particular, extreme precipitation usually lacks representation, which may introduce the bottleneck for radar QPE with machine learning models. Discovering the intrinsic characteristic of extreme precipitation with few samples is challenging. In this letter, we focus on the radar reflectivity data and aim to generate synthetic radar image sequences with respect to extreme precipitation. Considering the relatively long interval between continuous radar images due to radar volume scan, traditional methods in video generation are not suitable. In this letter, we propose Two-stage Generative Adversarial Networks (TsGANs) to address the above-mentioned problem. In general, our TsGAN constructs adversarial process between generators and discriminators: the generator produces samples similar to real data, while the discriminator determines whether or not a sample is eligible. In Stage I, we generate an image sequence containing content and motion features. In Stage II, we design an enhanced net structure to enrich the adversarial processes and further improve the motion features. Experimental testing is performed within the radar coverage in Shenzhen, China, on rainfall events in 2014-2016. Results show that our TsGAN is superior to previous works.

In this paper, we address the multiview nonlinear subspace representation problem. Traditional multiview subspace learning methods assume that the heterogeneous features of the data usually lie within the union of multiple linear subspaces. However, instead of linear subspaces, the data feature actually resides in multiple nonlinear subspaces in many real-world applications, resulting in unsatisfactory clustering performance. To overcome this, we propose a hyper-Laplacian regularized multilinear multiview self-representation model, which is referred to as HLR-M2VS, to jointly learn multiple views correlation and a local geometrical structure in a unified tensor space and view-specific self-representation feature spaces, respectively. In unified tensor space, a well-founded tensor low-rank regularization is adopted to impose on the self-representation coefficient tensor to ensure global consensus among different views. In view-specific feature space, hypergraph-induced hyper-Laplacian regularization is utilized to preserve the local geometrical structure embedded in a high-dimensional ambient space. An efficient algorithm is then derived to solve the optimization problem of the established model with theoretical convergence guarantee. Furthermore, the proposed model can be extended to semisupervised classification without introducing any additional parameters. An extensive experiment of our method is conducted on many challenging datasets, where a clear advance over state-of-the-art multiview clustering and multiview semisupervised classification approaches is achieved.

In the era of big data, data-driven fault detection is vital for modern industrial systems. This article considers the potential complexity of fault detection and proposes a novel nonlinear method based on nonnegative matrix factorization (NMF). Motivated by an autoencoder, in this article we first utilize the input data to learn an appropriate nonlinear mapping function, which transforms the original space into a high-dimensional feature space. Then, according to the decomposition rule of NMF, we divide the learned feature space into two subspaces, and two statistics in these subspaces are designed appropriately for nonlinear fault detection. The established method, i.e., deep nonnegative matrix factorization (DNMF), is implemented by three parts: an encoder module, an NMF module, and a decoder module. Unlike conventional NMF-based nonlinear methods using implicit and predetermined kernels, DNMF provides a new nonlinear scheme applied to NMF via a deep autoencoder framework and realizes nonlinear mapping for input data automatically. Our proposed nonlinear framework can be further generalized to other linear methods. Besides, DNMF greatly expands the NMF application scope by breaking through the limitation of nonnegative input. The Tennessee Eastman process as an industrial benchmark is employed to verify the effectiveness of the proposed method.

Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain. The key issue of domain adaptation is how to reduce the distribution discrepancy between two domains in a proper way such that they can be treated indifferently for learning. In this paper, we propose a novel domain adaptation approach, which can thoroughly explore the data distribution structure of target domain. Specifically, we regard the samples within the same cluster in target domain as a whole rather than individuals and assigns pseudo-labels to the target cluster by class centroid matching. Besides, to exploit the manifold structure information of target data more thoroughly, we further introduce a local manifold self-learning strategy into our proposal to adaptively capture the inherent local connectivity of target samples. An efficient iterative optimization algorithm is designed to solve the objective function of our proposal with theoretical convergence guarantee. In addition to unsupervised domain adaptation, we further extend our method to the semi-supervised scenario including both homogeneous and heterogeneous settings in a direct but elegant way. Extensive experiments on seven benchmark datasets validate the significant superiority of our proposal in both unsupervised and semi-supervised manners.

We propose Mask SSD, an efficient and effective approach to address the challenging instance segmentation task. Based on a single-shot detector, Mask SSD detects all instances in an image and marks the pixels that belong to each instance. It consists of a detection subnetwork that predicts object categories and bounding box locations, and an instance-level segmentation subnetwork that generates the foreground mask for each instance. In the detection subnetwork, multi-scale and feedback features from different layers are used to better represent objects of various sizes and provide high-level semantic information. Then, we adopt an assistant classification network to guide per-class score prediction, which consists of objectness prior and category likelihood. The instance-level segmentation subnetwork outputs pixel-wise segmentation for each detection while providing the multi-scale and feedback features from different layers as input. These two subnetworks are jointly optimized by a multi-task loss function, which renders Mask SSD direct prediction on detection and segmentation results. We conduct extensive experiments on PASCAL VOC, SBD, and MS COCO datasets to evaluate the performance of Mask SSD. Experimental results verify that as compared with state-of-the-art approaches, our proposed method has a comparable precision with less speed overhead.

Existing successful person re-identification (Re-ID) models often employ the part-level representation to extract the fine-grained information, but commonly use the loss that is particularly designed for global features, ignoring the relationship between semantic parts. In this paper, we present a novel triplet loss that emphasizes the salient parts and also takes the consideration of alignment. This loss is based on the crossing-bing matching metric that also known as Wasserstein Distance. It measures how much effort it would take to move the embeddings of local features to align two distributions, such that it is able to find an optimal transport matrix to re-weight the distance of different local parts. The distributions in support of local parts is produced via a new attention mechanism, which is calculated by the inner product between high-level global feature and local features, representing the importance of different semantic parts w.r.t. identification. We show that the obtained optimal transport matrix can not only distinguish the relevant and misleading parts, and hence assign different weights to them, but also rectify the original distance according to the learned distributions, resulting in an elegant solution for the mis-alignment issue. Besides, the proposed method is easily implemented in most Re-ID learning system with end-to-end training style, and can obviously improve their performance. Extensive experiments and comparisons with recent Re-ID methods manifest the competitive performance of our method.

This paper presents a tensor multi-task model for person re-identification (Re-ID). Due to discrepancy among cameras, our approach regards Re-ID from multiple cameras as different but related classification tasks, each task corresponding to a specific camera. In each task, we distinguish the person identity as a one-vs-all linear classification problem, where one classifier is associated with a specific person. By constructing all classifiers into a task-specific projection matrix, the proposed method could utilize all the matrices to form a tensor structure, and jointly train all the tasks in a uniform tensor space. In this space, by assuming the features of the same person under different cameras are generated from a latent subspace, and different identities under the same perspective share similar patterns, the high-order correlations, not only across different tasks but also within a certain task, can be captured by utilizing a new type of low-rank tensor constraint. Therefore, the learned classifiers transform the original feature vector into the latent space, where feature distributions across cameras can be well-aligned. Moreover, this model can be incorporated into multiple visual features to boost the performance, and easily extended to the unsupervised setting. Extensive experiments and comparisons with recent Re-ID methods manifest the competitive performance of our method.

This paper presents a novel deep learning framework for the inter-patient electrocardiogram (ECG) heartbeat classification. A symbolization approach especially designed for ECG is introduced, which can jointly represent the morphology and rhythm of the heartbeat and alleviate the influence of inter-patient variation through baseline correction. The symbolic representation of the heartbeat is used by a multi-perspective convolutional neural network (MPCNN) to learn features automatically and classify the heartbeat. We evaluate our method for the detection of the supraventricular ectopic beat (SVEB) and ventricular ectopic beat (VEB) on MIT-BIH arrhythmia dataset. Compared with the state-of-the-art methods based on manual features or deep learning models, our method shows superior performance: the overall accuracy of 96.4%, F1 scores for SVEB and VEB of 76.6% and 89.7%, respectively. The ablation study on our method validates the effectiveness of the proposed symbolization approach and joint representation architecture, which can help the deep learning model to learn more general features and improve the ability of generalization for unseen patients. Because our method achieves a competitive inter-patient heartbeat classification performance without complex handcrafted features or the intervention of the human expert, it can also be adjusted to handle various other tasks relative to ECG classification.

Recommendation technology is an important part of the Internet of Things (IoT) services, which can provide better service for users and help users get information anytime, anywhere. However, the traditional recommendation algorithms cannot meet user's fast and accurate recommended requirements in the IoT environment. In the face of a large-volume data, the method of finding neighborhood by comparing whole user information will result in a low recommendation efficiency. In addition, the traditional recommendation system ignores the inherent connection between user's preference and time. In reality, the interest of the user varies over time. Recommendation system should provide users accurate and fast with the change of time. To address this, we propose a novel recommendation model based on time correlation coefficient and an improved K-means with cuckoo search (CSK-means), called TCCF. The clustering method can cluster similar users together for further quick and accurate recommendation. Moreover, an effective and personalized recommendation model based on preference pattern (PTCCF) is designed to improve the quality of TCCF. It can provide a higher quality recommendation by analyzing the user's behaviors. The extensive experiments are conducted on two real datasets of MovieLens and Douban, and the precision of our model have improved about 5.2 percent compared with the MCoC model. Systematic experimental results have demonstrated our models TCCF and PTCCF are effective for IoT scenarios.

Internet of Things (IoT) equipment is usually in a harsh environment, and its security has always been a widely concerned issue. Node identity authentication is an important means to ensure its security. Traditional IoT identity authentication protocols usually rely on trusted third parties. However, many IoT environments do not allow such conditions, and are prone to single point failure. Blockchain technology with decentralization features provides a new solution for distributed IoT system. In this paper, a blockchain based multi-WSN authentication scheme for IoT is proposed. The nodes of IoT are divided into base stations, cluster head nodes and ordinary nodes according to their capability differences, which are formed to a hierarchical network. A blockchain network is constructed among different types of nodes to form a hybrid blockchain model, including local chain and public chain. In this hybrid model, nodes identity mutual authentication in various communication scenarios is realized, ordinary node identity authentication operation is accomplished by local blockchain, and cluster head node identity authentication are realized in public blockchain. The analysis of security and performance shows that the scheme has comprehensive security and better performance.

Summary It is difficult to protect users' privacy and to process private information due to the complexity and uncertainty of such information. To protect private information quickly and accurately, a many‐objective optimization algorithm framework based on the hybrid elite selection strategy is proposed in this paper. First, a mating selection mechanism combined with the achievement scale function and angle information index is used to generate elite offspring of the internal population. Then, the balanceable fitness estimation method is employed to select and update the external archive. To test performance, the proposed algorithm is tested on many‐objective optimization problems (MaOPs) and compared with five state‐of‐the‐art algorithms. Experimental simulation results show that the proposed algorithm is more effective in solving MaOPs and can inspire development of a better privacy protection strategy.

Weakly supervised learning is capable of achieving fine‐grained tasks with coarse annotations, which has shown great potential in computer‐aided diagnosis. This study aims to achieve thoracic disease diagnosis in a weakly supervised manner only with coarse image‐level annotations. Except for considering the performance of disease diagnosis, the study concentrates more on discovering the location of the pathological area which is used as visualised evidence for interpretability of diagnosis and the following retrospective analysis. To harvest more associated pathological areas, spatial non‐local attention mechanism to learn non‐local aware features is investigated. Further, a simple, effective, and widely applicable model ResNet‐spatial non‐local attention (SNA) is developed for these two objectives. Besides, an effective visualisation method compatible with the proposal is introduced. The effectiveness of the proposed ResNet‐SNA was validated on the large publicly available chest X‐ray dataset, ChestX‐ray14. Compared with the baseline model, the proposed model improved by 7.96% averaged over 14 diseases, achieving 0.8247 area under the scores up to the highest classification results compared with related works. For localisation, the proposed model improved the performance significantly without using any extra information. More importantly, the proposal only requires image‐level annotations without fine‐grained expertise, which is cost‐effective and expected to apply in clinical diagnosis.

The sequential decision-making problem with large-scale state spaces is an important and challenging topic for multitask reinforcement learning (MTRL). Training near-optimality policies across tasks suffers from prior knowledge deficiency in discrete-time nonlinear environment, especially for continuous task variations, requiring scalability approaches to transfer prior knowledge among new tasks when considering large number of tasks. This paper proposes a multitask policy adversarial learning (MTPAL) method for learning a nonlinear feedback policy that generalizes across multiple tasks, making cognizance ability of robot much closer to human-level decision making. The key idea is to construct a parametrized policy model directly from large high-dimensional observations by deep function approximators, and then train optimal of sequential decision policy for each new task by an adversarial process, in which simultaneously two models are trained: a multitask policy generator transforms samples drawn from a prior distribution into samples from a complex data distribution with higher dimensionality, and a multitask policy discriminator decides whether the given sample is prior distribution from human-level empirically derived or from the generator. All the related human-level empirically derived are integrated into the sequential decision policy, transferring human-level policy at every layer in a deep policy network. Extensive experimental testing result of four different WeiChai Power manufacturing data sets shows that our approach can surpass human performance simultaneously from cart-pole to production assembly control.

Multi-index fusion has demonstrated impressive performances in the retrieval task by integrating different visual representations in a unified framework. However, previous works mainly consider propagating similarities via a neighbor structure, ignoring the high-order information among different visual representations. In this paper, we propose a new multi-index fusion scheme for image retrieval. By formulating this procedure as a multilinear-based optimization problem, the complementary information hidden in different indexes can be explored more thoroughly. Specifically, we first build our multiple indexes from various visual representations. Then, a so-called index-specific functional matrix, which aims to propagate similarities, is introduced to update the original index. The functional matrices are then optimized in a unified tensor space to achieve a refinement, such that the relevant images can be pushed closer. The optimization problem can be efficiently solved by the augmented Lagrangian method with a theoretical convergence guarantee. Unlike the traditional multi-index fusion scheme, our approach embeds the multi-index subspace structure into the new indexes with sparse constraint and, thus, it has little additional memory consumption in the online query stage. Experimental evaluation on three benchmark datasets reveals that the proposed approach achieves state-of-the-art performance, that is, N-score 3.94 on UKBench, mAP 94.1% on Holiday, and 62.39% on Market-1501.

Knowledge graphs have proven to be incredibly useful for many artificial intelligence applications. Although typical knowledge graphs may contain a huge amount of facts, they are far from being complete, which motivates an increasing research interest in learning statistical models for knowledge graph completion. Learning such models relies on sampling appropriate number of negative examples, as only the positive examples are contained in the data set. However, this would introduce errors or heuristic biases which restrict the sampler to visit other potentially reliable negative examples for better prediction models. In this paper, we present a novel perspective on skillfully selecting the negative examples for knowledge graph completion. We develop a two-stage logistic regression filter under the positive-unlabeled learning (PU learning) framework, which enables an automatic and iterative refinement of the negative candidate pools. We then contrast positive examples with the resulting negative ones based on the improved embedding-based models. In particular, we work with a cost-sensitive loss function by weighting the semantic differences between negative examples and particular positive ones. This weighting scheme reflects the importance of predicting the preferences between them correctly. In experiments, we validate the effectiveness of negative examples in refining and weighting schemes, respectively. Besides this, our proposed prediction model also outperforms the state-of-the-art methods on two public datasets.

An accurate, high-resolution precipitation estimation based on rain gauge and radar observations is essential in various meteorological applications. Although numerous studies have demonstrated the effectiveness of merging two information sources rather than using separate sources, approaches that simultaneously consider the local radar reflectivity, the neighborhood rain gauge observations, and the temporal information are much less common. In this paper, we present a new framework for real-time quantitative precipitation estimation (QPE). By formulating the QPE as a continuous conditional random field (CCRF) learning problem, the spatiotemporal correlations of precipitation can be explored more thoroughly. Based on the CCRF, we further improve the accuracy of the precipitation estimation by introducing geographical and temporal attention. Specifically, we first present a data-driven weighting scheme to merge the first law of geography into the proposed framework, and hence, the neighborhood sample closer to the estimated grid can receive more attention. Second, the temporal attention penalizes the similarity between two adjacent timestamps via the discrepancy of two-view estimates, which can model the local temporal consistency and tolerate some drastic changes. A sufficient evaluation is conducted on 11 rainfall processes that occurred in 2015, and the results confirm the advantage of our proposal for real-time precipitation estimation.

Multi-class imbalanced problems have attracted growing attention from the real-world classification tasks in engineering. The underlying skewed distribution of multiple classes poses difficulties for learning algorithms, which becomes more challenging when considering overlapping between classes, lack of representative data, and mixed-type data. In this work, we address this problem in a data-oriented way. Motivated by a recently proposed over-sampling technique designed for numeric data sets, Mahalanobis Distance-based Over-sampling (MDO), we use this technique to capture the covariance structure of the minority class and to generate synthetic samples along the probability contours for learning algorithms. Based on MDO, we further improve the over-sampling strategy and generalize it for mixed-type data sets. The established technique, Adaptive Mahalanobis Distance-based Over-sampling (AMDO), introduces GSVD (Generalized Singular Value Decomposition) for mixed-type data, develops a partially balanced resampling scheme and optimizes the sample synthesis. Theoretical analysis is conducted to demonstrate the reasonability of AMDO. Extensive experimental testing is performed on 15 multi-class imbalanced benchmarks and two data sets for precipitation phase recognition in comparison with several state-of-the-art multi-class imbalanced learning methods. The results validate the effectiveness and robustness of our proposal.

In this paper, we propose a bioinspired model for human action recognition through modeling neural mechanisms of information processing in two visual cortical areas: the primary visual cortex (V1) and the middle temporal cortex (MT) dedicated to motion. This model, named V1-MT, is composed of V1 and MT models (layers) corresponding to their cortical areas, which are built with layered spiking neural networks (SNNs). Some neuron properties in V1 and MT, such as direction and speed selectivity, spatiotemporal inseparability, and center surround suppression, are integrated into SNNs. Based on speed and direction selectivity, V1 and MT models contain multiple SNN channels, each of which processes motion information in sequences with spatiotemporal tunings of neurons at a certain speed and different directions. Therefore, we propose two operations, input signal perceiving with 3-D Gabor filters and surround inhibition processing with 3-D differences of Gaussian functions, to perform this task according to the spatiotemporal inseparability and center surround suppression of neurons. Then, neurons are modeled with our simplified integrate-and-fire model and motion information is transformed into spike trains. Afterward, we define a new feature vector: a mean motion map computed from spike trains in all channels to represent human actions. Finally, a support vector machine is trained to classify actions represented by the feature vectors. We conducted extensive experiments on public action databases, and the results show that our model outperforms other bioinspired models and rivals the state-of-the-art approaches.

Multitask learning has shown great potentiality for visual tracking under a particle filter framework. However, the recent multitask trackers, which exploit the similarity between all candidates by imposing group sparsity on the candidate representations, have a limitation in robustness due to the diverse sampling of candidates. To deal with this issue, we propose a discriminative reverse sparse tracker via weighted multitask learning. Our positive and negative templates are retained from the target observations and the background, respectively. Here, the templates are reversely represented via the candidates, and the representation of each positive template is viewed as a single task. Compared with existing multitask trackers, the proposed algorithm has the following advantages. First, we regularize the target representations with the ℓ2,1-norm to exploit the similarity shared by the positive templates, which is reasonable because of the target appearance consistency in the tracking process. Second, the valuable prior relationship between the candidates and the templates is introduced into the representation model by a weighted multitask learning scheme. Third, both target information and background information are integrated to generate discriminative scores for enhancing the proposed tracker. The experimental results on challenging sequences show that the proposed algorithm is effective and performs favorably against 12 state-of-the-art trackers.

An effective representation model, which aims to mine the most meaningful information in the data, plays an important role in visual tracking. Some recent particle-filter-based trackers achieve promising results by introducing the low-rank assumption into the representation model. However, their assumed low-rank structure of candidates limits the robustness when facing severe challenges such as abrupt motion. To avoid the above limitation, we propose a temporal restricted reverse-low-rank learning algorithm for visual tracking with the following advantages: 1) the reverse-low-rank model jointly represents target and background templates via candidates, which exploits the low-rank structure among consecutive target observations and enforces the temporal consistency of target in a global level; 2) the appearance consistency may be broken when target suffers from sudden changes. To overcome this issue, we propose a local constraint via 11,2 mixed-norm, which can not only ensures the local consistency of target appearance, but also tolerates the sudden changes between two adjacent frames; and 3) to alleviate the inference of unreasonable representation values due to outlier candidates, an adaptive weighted scheme is designed to improve the robustness of the tracker. By evaluating on 26 challenge video sequences, the experiments show the effectiveness and favorable performance of the proposed algorithm against 12 state-of-the-art visual trackers.

In this paper, we propose a new low-rank and sparse representation model for moving object detection. The model preserves the natural space-time structure of video sequences by representing them as three-way tensors. Then, it operates the low-rank background and sparse foreground decomposition in the tensor framework. On the one hand, we use the tensor nuclear norm to exploit the spatio-temporal redundancy of background based on the circulant algebra. On the other, we use the new designed saliently fused-sparse regularizer (SFS) to adaptively constrain the foreground with spatio-temporal smoothness. To refine the existing foreground smooth regularizers, the SFS incorporates the local spatio-temporal geometric structure information into the tensor total variation by using the 3D locally adaptive regression kernel (3D-LARK). What is more, the SFS further uses the 3D-LARK to compute the space-time motion saliency of foreground, which is combined with the l1norm and improves the robustness of foreground extraction. Finally, we solve the proposed model with globally optimal guarantee. Extensive experiments on challenging well-known data sets demonstrate that our method significantly outperforms the state-of-the-art approaches and works effectively on a wide range of complex scenarios.

In this paper, we propose a new low-rank tensor model based on the circulant algebra, namely, twist tensor nuclear norm (t-TNN). The twist tensor denotes a three-way tensor representation to laterally store 2-D data slices in order. On one hand, t-TNN convexly relaxes the tensor multirank of the twist tensor in the Fourier domain, which allows an efficient computation using fast Fourier transform. On the other, t-TNN is equal to the nuclear norm of block circulant matricization of the twist tensor in the original domain, which extends the traditional matrix nuclear norm in a block circulant way. We test the t-TNN model on a video completion application that aims to fill missing values and the experiment results validate its effectiveness, especially when dealing with video recorded by a nonstationary panning camera. The block circulant matricization of the twist tensor can be transformed into a circulant block representation with nuclear norm invariance. This representation, after transformation, exploits the horizontal translation relationship between the frames in a video, and endows the t-TNN model with a more powerful ability to reconstruct panning videos than the existing state-of-the-art low-rank models.

Radar-based rainfall estimation is one of the most important inputs for various meteorological applications. Although exciting progresses have been made in this area, accurate real-time rainfall estimation is still a significant opening topic that requires practical modeling. The research study presented in this letter improves rainfall estimation accuracy by proposing a random forest and linear chain conditional random-field-based spatiotemporal model (RANLIST). To apply this model for rainfall estimation, the implementing approach is presented. The advantages are listed as follows: 1) RANLIST improves rainfall estimation accuracy by exploiting both underlying local spatial structure of multiple radar reflectivity factors and time-series information of rain processes. 2) The time-series information of rain processes can be utilized in virtue of the presented implementation method. Experiments have been carried out over the radar-covered area of Quanzhou, China, in June and July 2014. Results show that RANLIST is superior to previous works.

Mutlilabel classification arises in various domains including computer vision and machine learning. Given a single instance, multilabel classification aims to learn a set of labels simultaneously. However, existing methods fail to address two key problems: 1) exploiting correlations among instances and 2) reducing computational complexity. In this letter, we propose a new semisupervised multilabel classification algorithm with joint dimensionality reduction. First, an elaborate matrix is designed for evaluating instance similarity; thus, it can take both labeled and unlabeled instances into consideration. Second, a linear dimensionality reduction matrix is added into the framework of multilabel classification. Besides, the dimensionality reduction matrix and the objective function can be optimized simultaneously. Finally, we design an efficient algorithm to solve the dual problem of the proposed model. Experiment results demonstrate that the proposed method is effective and promising.

Hyperspectral images (HSIs) are inevitably corrupted by mixture noise during their acquisition process, in which various kinds of noise, e.g., Gaussian noise, impulse noise, dead lines, and stripes, may exist concurrently. In this paper, mixture noise removal is well illustrated by the task of recovering the low-rank and sparse components of a given matrix, which is constructed by stacking vectorized HSI patches from all the bands at the same position. Instead of applying a traditional nuclear norm, a nonconvex low-rank regularizer, i.e., weighted Schatten p-norm (WSN), is introduced to not only give better approximation to the original low-rank assumption but also to consider the importance of different rank components. The resulted nonconvex low-rank matrix approximation (LRMA) model falls into the applicable scope of an augmented Lagrangian method, and its WSN minimization subproblem can be efficiently solved by generalized iterated shrinkage algorithm. Moreover, the proposed model is integrated into an iterative regularization schema to produce final results, leading to a completed HSI restoration framework. Extensive experimental testing on simulated and real data shows, both qualitatively and quantitatively, that the proposed method has achieved highly competent objective performance compared with several state-of-the-art HSI restoration methods.

Large-scale machine coordination is a primary approach for flexible manufacturing, enabling large-scale autonomous machines to dynamically coordinate their actions in pursuit of a custom task. One of the key challenges for such large-scale systems is finding high-dimensional coordination decision-making policies. Multitask policy gradient algorithms can be used in search of high-dimensional policies, particularly in collaborative decision support systems and distributed control systems. However, it is difficult for these algorithms to learn online high-dimensional coordination control policies (CCP) from large-scale custom manufacturing tasks. This paper proposes a large-scale online multitask learning and decision-making approach, which can consecutively learn high-dimensional CCP in order to quickly coordinate machine actions online for large-scale custom manufacturing task. A large-scale online multitask leaning algorithm is developed, which is able to learn large-scale high-dimensional CCP in a flexible manufacturing scenario. An online stochastic planning algorithm is proposed, which online optimizes the Markov network structure in order to avoid expensive global search for the optimal policy. Experiments have been undertaken using a professional flexible manufacturing testbed deployed within a smart factory of Weichai Power in China. Results show the proposed approach to be more efficient when compared with previous works.

Low rank matrix approximation (LRMA), which aims to recover the underlying low rank matrix from its degraded observation, has a wide range of applications in computer vision. The latest LRMA methods resort to using the nuclear norm minimization (NNM) as a convex relaxation of the nonconvex rank minimization. However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications. We propose a more flexible model, namely, the weighted Schatten p-norm minimization (WSNM), to generalize the NNM to the Schatten p-norm minimization with weights assigned to different singular values. The proposed WSNM not only gives better approximation to the original low-rank assumption, but also considers the importance of different rank components. We analyze the solution of WSNM and prove that, under certain weights permutation, WSNM can be equivalently transformed into independent non-convex lp-norm subproblems, whose global optimum can be efficiently solved by generalized iterated shrinkage algorithm. We apply WSNM to typical low-level vision problems, e.g., image denoising and background subtraction. Extensive experimental results show, both qualitatively and quantitatively, that the proposed WSNM can more effectively remove noise, and model the complex and dynamic scenes compared with state-of-the-art methods.

It remains a challenge to simultaneously remove geometric distortion and space-time-varying blur in frames captured through a turbulent atmospheric medium. To solve, or at least reduce these effects, we propose a new scheme to recover a latent image from observed frames by integrating a new hybrid total variation model and deformation-guided spatial-temporal kernel regression. The proposed scheme first constructs a high-quality reference image from the observed frames using low-rank decomposition. Then, to generate an improved registered sequence, the reference image is iteratively optimized using a variational model containing the combined regularization of local and non-local total variations. The proposed optimization algorithm efficiently solves this model with convergence guarantee. Next, to reduce blur variation, deformation-guided spatial-temporal kernel regression is carried out to fuse the registered sequence into one image by introducing the concept of the near-stationary patch. Applying a blind deconvolution algorithm to the fused image produces the final output. Extensive experimental testing shows, both qualitatively and quantitatively, that the proposed method can effectively alleviate distortion, and blur and recover details of the original scene compared to the state-of-the-art methods.

We propose a robust tracking algorithm based on local sparse coding with discriminative dictionary learning and new keypoint matching schema. This algorithm consists of two parts: the local sparse coding with online updated discriminative dictionary for tracking (SOD part), and the keypoint matching refinement for enhancing the tracking performance (KP part). In the SOD part, the local image patches of the target object and background are represented by their sparse codes using an over-complete discriminative dictionary. Such discriminative dictionary, which encodes the information of both the foreground and the background, may provide more discriminative power. Furthermore, in order to adapt the dictionary to the variation of the foreground and background during the tracking, an online learning method is employed to update the dictionary. The KP part utilizes refined keypoint matching schema to improve the performance of the SOD. With the help of sparse representation and online updated discriminative dictionary, the KP part are more robust than the traditional method to reject the incorrect matches and eliminate the outliers. The proposed method is embedded into a Bayesian inference framework for visual tracking. Experimental results on several challenging video sequences demonstrate the effectiveness and robustness of our approach.

In this paper, a novel supervised dimensionality reduction method based on LLE is put forward, which is titled locally linear representation Fisher criterion (LLRFC). In the proposed LLRFC, the class information of the original data has been fully considered, according to which an inter-class graph and an intra-class graph can be well modeled respectively. Meanwhile, the neighborhoods in the inter-class graph consist of samples with various labels and the neighborhoods in the intra-graph are just composed of points sampled from the same class. Then the least locally linear representation technique is introduced to optimize the reconstruction weights in both graphs. At last, the Fisher criterion with maximum inter-class scatter and minimum intra-class scatter is reasoned. Experiments on some benchmark face data sets have been conducted and the results validate the proposed method's performance.

This paper aims to conduct a study on the listwise approach to learning to rank. The listwise approach learns a ranking function by taking individual lists as instances and minimizing a loss function defined on the predicted list and the ground-truth list. Existing work on the approach mainly focused on the development of new algorithms; methods such as RankCosine and ListNet have been proposed and good performances by them have been observed. Unfortunately, the underlying theory was not sufficiently studied so far. To amend the problem, this paper proposes conducting theoretical analysis of learning to rank algorithms through investigations on the properties of the loss functions, including consistency, soundness, continuity, differentiability, convexity, and efficiency. A sufficient condition on consistency for ranking is given, which seems to be the first such result obtained in related research. The paper then conducts analysis on three loss functions: likelihood loss, cosine loss, and cross entropy loss. The latter two were used in RankCosine and ListNet. The use of the likelihood loss leads to the development of a new listwise method called ListMLE, whose loss function offers better properties, and also leads to better experimental results.

Most existing algorithms for ordinal regression usually seek an orientation for which the projected samples are well separated, and seriate intervals on that orientation to represent the ranks. However, these algorithms only make use of one dimension in the sample space, which would definitely lose some useful information in its complementary subspace. As a remedy, we propose an algorithm framework for ordinal regression which consists of two phases: recursively extracting features from the decreasing subspace and learning a ranking rule from the examples represented by the new features. In this framework, every algorithm that projects samples onto a line can be used as a feature extractor and features with decreasing ranking ability are extracted one by one to make best use of the information contained in the training samples. Experiments on synthetic and benchmark datasets verify the usefulness of our framework.