Query：
学者姓名：王石平
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are tailored for scenarios with fixed data views, falling short of emulating the intricate cognitive procedures of the human brain processing signals sequentially. Our cerebral architecture seamlessly integrates sequential data through intricate feed-forward and feedback mechanisms. In stark contrast, traditional methods struggle to generalize effectively when confronted with data spanning diverse domains, highlighting the need for innovative strategies that can mimic the brain's adaptability and dynamic integration capabilities. In this paper, we propose a bio-neurologically inspired multiview incremental framework named MVIL aimed at emulating the brain's fine-grained fusion of sequentially arriving views. MVIL lies two fundamental modules: structured Hebbian plasticity and synaptic partition learning. The structured Hebbian plasticity reshapes the structure of weights to express the high correlation between view representations, facilitating a fine-grained fusion of view representations. Moreover, synaptic partition learning is efficient in alleviating drastic changes in weights and also retaining old knowledge by inhibiting partial synapses. These modules bionically play a central role in reinforcing crucial associations between newly acquired information and existing knowledge repositories, thereby enhancing the network's capacity for generalization. Experimental results on six benchmark datasets show MVIL's effectiveness over state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Contrastive Learning Contrastive Learning Reinforcement learning Reinforcement learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Yuhong , Song, Ailin , Yin, Huifeng et al. Multi-View Incremental Learning with Structured Hebbian Plasticity for Enhanced Fusion Efficiency [C] . 2025 : 1265-1273 . |
| MLA | Chen, Yuhong et al. "Multi-View Incremental Learning with Structured Hebbian Plasticity for Enhanced Fusion Efficiency" . (2025) : 1265-1273 . |
| APA | Chen, Yuhong , Song, Ailin , Yin, Huifeng , Zhong, Shuai , Chen, Fuhai , Xu, Qi et al. Multi-View Incremental Learning with Structured Hebbian Plasticity for Enhanced Fusion Efficiency . (2025) : 1265-1273 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In the context of Cyber Physical Social Intelligence (CPSI), efficiently training and inferring from samples with limited labels poses critical challenges due to the scarcity and high cost of label acquisition for big data. The aim is to attain high accuracy at minimal cost, thereby enhancing adaptation to the CPSI scenario. To tackle the challenges in CPSI, we present a multi-level feature learning framework for semi-supervised classification tasks. Initially, we employ a mapping operation for each view, extracting view-specific features with a feature-level reconstruction loss. These features are fused to obtain a shared feature. Simultaneously, a learnable graph neural network captures global topology using a graph structure-level reconstruction loss. Subsequently, a scalable graph convolution fusion module combines these features. Our evaluations on eight benchmark datasets show promising results and empirically prove the effectiveness of our approach, surpassing eight state-of-the-art methods in multi-view semi-supervised classification tasks. © 2018 Tsinghua University Press.
Keyword ：
Graph neural networks Graph neural networks Intelligent computing Intelligent computing Intelligent systems Intelligent systems Multi-task learning Multi-task learning Self-supervised learning Self-supervised learning Semi-supervised learning Semi-supervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Song, Na , Yang, Jing , Fu, Xuemei et al. Hierarchical Semi-Supervised Representation Learning for Cyber Physical Social Intelligence [J]. | Big Data Mining and Analytics , 2025 , 8 (4) : 837-850 . |
| MLA | Song, Na et al. "Hierarchical Semi-Supervised Representation Learning for Cyber Physical Social Intelligence" . | Big Data Mining and Analytics 8 . 4 (2025) : 837-850 . |
| APA | Song, Na , Yang, Jing , Fu, Xuemei , Yang, Xiangli , Xie, Ying , Wang, Shiping . Hierarchical Semi-Supervised Representation Learning for Cyber Physical Social Intelligence . | Big Data Mining and Analytics , 2025 , 8 (4) , 837-850 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained; 2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Deep learning Deep learning Multi-task learning Multi-task learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Du, Shide , Fang, Zihan , Tan, Yanchao et al. OpenViewer: Openness-Aware Multi-View Learning [C] . 2025 : 16389-16397 . |
| MLA | Du, Shide et al. "OpenViewer: Openness-Aware Multi-View Learning" . (2025) : 16389-16397 . |
| APA | Du, Shide , Fang, Zihan , Tan, Yanchao , Wang, Changwei , Wang, Shiping , Guo, Wenzhong . OpenViewer: Openness-Aware Multi-View Learning . (2025) : 16389-16397 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The analysis and mining of multi-view data have gained widespread attention, making multi-view anomaly detection a prominent research area. Despite notable advancements in the performance of existing multi-view anomaly detection methods, they still face certain limitations. (1) The existing methods fail to fully leverage the low-rank structure of multi-view data, which results in a lack of necessary interpretability when uncovering the latent relationships between views. (2) In the recovery of the consensus structure, the current methods achieve this merely through a simple aggregation process, lacking in-depth exploration and interaction between the potential structures of each view. To address these challenges, we propose the Low-Rank Tucker Decomposition based on Meta-Learning (LRTDM) for multi-view outlier detection. First, the low-rank Tucker decomposition is employed to reveal the low-rank structure of the multi-view self-expressive tensor. The factor matrices and core tensor effectively preserve and encode the latent structure of each view. This structured representation can efficiently capture the potential shared features between views, allowing for a more refined analysis of each individual view. Furthermore, meta-learning is utilized to define the learning and fusion of view-specific latent features as a nested optimization problem, which is solved alternately using a two-layer optimization scheme. Finally, anomalies are detected through the consensus matrix recovered from the latent representations and the error matrix during the self-expressive tensor learning process. Extensive experiments conducted on five publicly available datasets demonstrate the effectiveness of our approach. The results show that our algorithm improves detection accuracy by 2% to 10% compared to state-of-the-art methods. © 2025 Elsevier B.V.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Wei , Xie, Kun , Li, Jiayin et al. Low-rank tucker decomposition for multi-view outlier detection based on meta-learning [J]. | Information Fusion , 2025 , 123 . |
| MLA | Lin, Wei et al. "Low-rank tucker decomposition for multi-view outlier detection based on meta-learning" . | Information Fusion 123 (2025) . |
| APA | Lin, Wei , Xie, Kun , Li, Jiayin , Wang, Shiping , Xu, Li . Low-rank tucker decomposition for multi-view outlier detection based on meta-learning . | Information Fusion , 2025 , 123 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Multi-view learning has demonstrated strong potential in processing data from different sources or viewpoints. Despite the significant progress made by Multi-view Graph Neural Networks (MvGNNs) in exploiting graph structures, features, and representations, existing research generally lacks architectures specifically designed for the intrinsic properties of multi-view data. This leads to models that still have deficiencies in fully utilizing consistent and complementary information in multi-view data. Most of current research tends to simply extend the single-view GNN framework to multi-view data, lacking in-depth strategies to handle and leverage the unique properties of these data. To address this issue, we propose a simple yet effective MvGNN framework called Multi-view Representation Learning with Decoupled private and shared Propagation (MvRL-DP). This framework enables multi-view data to be effectively processed as a whole by alternating private and shared operations to integrate cross-view information. In addition, to address possible inconsistencies between views, we present a discriminative loss that promotes class separability and prevents the model from being misled by noise hidden in multi-view data. Experiments demonstrate that the proposed framework is superior to current state-of-the-art methods in the multi-view semi-supervised classification task.
Keyword ：
Multi-view learning Multi-view learning Propagation decoupling Propagation decoupling Representation learning Representation learning Semi-supervised classification Semi-supervised classification Tensor operation Tensor operation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Xuzheng , Lan, Shiyang , Wu, Zhihao et al. Multi-view Representation Learning with Decoupled private and shared Propagation [J]. | KNOWLEDGE-BASED SYSTEMS , 2025 , 310 . |
| MLA | Wang, Xuzheng et al. "Multi-view Representation Learning with Decoupled private and shared Propagation" . | KNOWLEDGE-BASED SYSTEMS 310 (2025) . |
| APA | Wang, Xuzheng , Lan, Shiyang , Wu, Zhihao , Guo, Wenzhong , Wang, Shiping . Multi-view Representation Learning with Decoupled private and shared Propagation . | KNOWLEDGE-BASED SYSTEMS , 2025 , 310 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Asa promising area in machine learning, multi-view learning enhances model performance by integrating data from various views. With the rise of graph convolutional networks, many studies have explored incorporating them into multi-view learning frameworks. However, these methods often require storing the entire graph topology, leading to significant memory demands. Additionally, iterative update operations in graph convolutions lead to longer inference times, making it difficult to deploy existing multi-view learning models on large graphs. To overcome these challenges, we introduce an efficient multi-view graph convolutional network via local aggregation and global propagation. In the local aggregation module, we use a structure-aware matrix for feature aggregation, which significantly reduces computational complexity compared to traditional graph convolutions. After that, we design a global propagation module that allows the model to be trained in batches, enabling deployment on large-scale graphs. Finally, we introduce the attention mechanism into multi-view feature fusion to more effectively explore the consistency and complementarity between views. The proposed method is employed to perform multi-view semi-supervised classification, and comprehensive experimental results on benchmark datasets validate its effectiveness.
Keyword ：
Graph neural networks Graph neural networks Local aggregation Local aggregation Multi-view learning Multi-view learning Representation learning Representation learning Semi-supervised classification Semi-supervised classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Lu , Shi, Yongquan , Pi, Yueyang et al. Efficient multi-view graph convolutional networks via local aggregation and global propagation [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 266 . |
| MLA | Liu, Lu et al. "Efficient multi-view graph convolutional networks via local aggregation and global propagation" . | EXPERT SYSTEMS WITH APPLICATIONS 266 (2025) . |
| APA | Liu, Lu , Shi, Yongquan , Pi, Yueyang , Guo, Wenzhong , Wang, Shiping . Efficient multi-view graph convolutional networks via local aggregation and global propagation . | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 266 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Topological structures of real-world graphs often exhibit heterogeneity involving diverse nodes and relation types. In recent years, heterogeneous graph learning methods utilizing meta-paths to capture composite relations and guide neighbor selection have garnered considerable attention. However, meta-path based approaches may establish connections between nodes of different categories while overlooking relations between nodes of the same category, decreasing the quality of node embeddings. In light of this, this paper proposes a Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction (HGNN-AR2) that adaptively adjusts the relations to alleviate connection deficiencies and heteromorphic issues. HGNNAR2 is grounded on distinct connections derived from multiple meta-paths. By examining the homomorphic correlations of latent features from each meta-path, we reshape the cross-node connections to explore the pertinent latent relations. Through the relation reconstruction, we unveil unique connections reflected by each meta-path and incorporate them into graph convolutional networks for more comprehensive representations. The proposed model is evaluated on various benchmark heterogeneous graph datasets, demonstrating superior performance compared to state-of-the-art competitors.
Keyword ：
Graph augmentation Graph augmentation Graph learning Graph learning Graph neural networks Graph neural networks Heterogeneous information networks Heterogeneous information networks Semi-supervised classification Semi-supervised classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Weihong , Chen, Zhaoliang , Chen, Yuhong et al. Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction [J]. | NEURAL NETWORKS , 2025 , 187 . |
| MLA | Lin, Weihong et al. "Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction" . | NEURAL NETWORKS 187 (2025) . |
| APA | Lin, Weihong , Chen, Zhaoliang , Chen, Yuhong , Wang, Shiping . Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction . | NEURAL NETWORKS , 2025 , 187 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recent studies highlight the growing appeal of multi-view learning due to its enhanced generalization. Semi-supervised classification, using few labeled samples to classify the unlabeled majority, is gaining popularity for its time and cost efficiency, particularly with high-dimensional and large-scale multi-view data. Existing graph-based methods for multi-view semi-supervised classification still have potential for improvement in further enhancing classification accuracy. Since deep random walk has demonstrated promising performance across diverse fields and shows potential for semi-supervised classification. This paper proposes a deep random walk inspired multi-view graph convolutional network model for semi-supervised classification tasks that builds signal propagation between connected vertices of the graph based on transfer probabilities. The learned representation matrices from different views are fused by an aggregator to learn appropriate weights, which are then normalized for label prediction. The proposed method partially reduces overfitting, and comprehensive experiments show it delivers impressive performance compared to other state-of-the-art algorithms, with classification accuracy improving by more than 5% on certain test datasets.
Keyword ：
Deep random walk Deep random walk Graph convolutional networks Graph convolutional networks Multi-view learning Multi-view learning Semi-supervised classification Semi-supervised classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Zexi , Chen, Weibin , Yao, Jie et al. Deep random walk inspired multi-view graph convolutional networks for semi-supervised classification [J]. | APPLIED INTELLIGENCE , 2025 , 55 (6) . |
| MLA | Chen, Zexi et al. "Deep random walk inspired multi-view graph convolutional networks for semi-supervised classification" . | APPLIED INTELLIGENCE 55 . 6 (2025) . |
| APA | Chen, Zexi , Chen, Weibin , Yao, Jie , Li, Jinbo , Wang, Shiping . Deep random walk inspired multi-view graph convolutional networks for semi-supervised classification . | APPLIED INTELLIGENCE , 2025 , 55 (6) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, heterogeneous graphs have attracted widespread attention as a powerful and practical superclass of traditional homogeneous graphs, which reflect the multi-type node entities and edge relations in the real world. Most existing methods adopt meta-path construction as the mainstream to learn long-range heterogeneous semantic messages between nodes. However, such schema constructs the node-wise correlation by connecting nodes via pre-computed fixed paths, which neglects the diversities of meta-paths on the path type and path range. In this paper, we propose a meta-path-based semantic embedding schema, which is called Heterogeneous Graph Embedding with Dual Edge Differentiation (HGE-DED) to adequately construct flexible meta-path combinations thus learning the rich and discriminative semantic of target nodes. Concretely, HGEDED devises a Multi-Type and multi-Range Meta-Path Construction (MTR-MP Construction), which covers the comprehensive exploration of meta-path combinations from path type and path range, expressing the diversity of edges at more fine-grained scales. Moreover, HGE-DED designs the semantics and meta-path joint guidance, constructing a hierarchical short- and long-range relation adjustment, which constrains the path learning as well as minimizes the impact of edge heterophily on heterogeneous graphs. Experimental results on four benchmark datasets demonstrate the effectiveness of HGE-DED compared with state-of-the-art methods.
Keyword ：
Graph neural network Graph neural network Heterogeneous information network Heterogeneous information network Meta-path combination Meta-path combination Semantic embedding Semantic embedding Semi-supervised classification Semi-supervised classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Yuhong , Chen, Fuhai , Wu, Zhihao et al. Heterogeneous Graph Embedding with Dual Edge Differentiation [J]. | NEURAL NETWORKS , 2025 , 183 . |
| MLA | Chen, Yuhong et al. "Heterogeneous Graph Embedding with Dual Edge Differentiation" . | NEURAL NETWORKS 183 (2025) . |
| APA | Chen, Yuhong , Chen, Fuhai , Wu, Zhihao , Chen, Zhaoliang , Cai, Zhiling , Tan, Yanchao et al. Heterogeneous Graph Embedding with Dual Edge Differentiation . | NEURAL NETWORKS , 2025 , 183 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Active learning, as a technique, aims to effectively label specific data points while operating within a designated query budget. Nevertheless, the majority of unsupervised active learning algorithms are based on shallow linear representation and lack sufficient interpretability. Furthermore, certain diversity-based methods face challenges in selecting samples that adequately represent the entire data distribution. Inspired by these reasons, in this paper, we propose an unsupervised active learning method on orthogonal projections to construct a deep neural network model. By optimizing the orthogonal projection process, we establish the connection between projection and active learning, consequently enhancing the interpretability of the proposed method. The proposed method can efficiently project the feature space onto a spanned subspace, deriving an indicator matrix while calculating the projection loss. Moreover, we consider the redundancy among samples to ensure both data point diversity and enhancement of clustering-based algorithms. Through extensive comparative experiments on six public datasets, the results demonstrate that the proposed method can effectively select more informative and representative samples and improve performance by up to 11%.
Keyword ：
Active learning Active learning deep learning deep learning differentiable networks differentiable networks machine learning machine learning orthogonal projection orthogonal projection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Pi, Yueyang , Shi, Yiqing , Du, Shide et al. Unsupervised Projected Sample Selector for Active Learning [J]. | IEEE TRANSACTIONS ON BIG DATA , 2025 , 11 (2) : 485-498 . |
| MLA | Pi, Yueyang et al. "Unsupervised Projected Sample Selector for Active Learning" . | IEEE TRANSACTIONS ON BIG DATA 11 . 2 (2025) : 485-498 . |
| APA | Pi, Yueyang , Shi, Yiqing , Du, Shide , Huang, Yang , Wang, Shiping . Unsupervised Projected Sample Selector for Active Learning . | IEEE TRANSACTIONS ON BIG DATA , 2025 , 11 (2) , 485-498 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
