Guang-Yu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Guang-Yu Zhang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Dong Huang
South China Agricultural University
9 shared publications - Chang-Dong Wang
Sun Yat-sen University
5 shared publications - Haiyan Wang
South China Agricultural University
2 shared publications - Jinrong Cui
College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China
2 shared publications - Wanrong Gu
South China Agricultural University
2 shared publications - Bin Zhang
Guangdong Institute of Intelligence Science and Technology, Hengqin, China
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 15853-15865
One-Step Anchor-Guided Multi-View Clustering via Tensor-Consistent Graph Factorization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 15853-15865
One-Step Anchor-Guided Multi-View Clustering via Tensor-Consistent Graph Factorization
- 12 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 107954
Structure-preserving contrastive graph clustering with dual-channel label alignment
- 12 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 107954
Structure-preserving contrastive graph clustering with dual-channel label alignment
- 26 July 2025
- Published by Springer Nature
- p. 482-494
Multi-scale Multi-order Attributed Graph Clustering
- 26 July 2025
- Published by Springer Nature
- p. 482-494
Multi-scale Multi-order Attributed Graph Clustering
- Open Access
- 22 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (4) , 1-21
Large-Scale Tensorized Multi-View Kernel Subspace Clustering
The anchor-based multi-view subspace clustering (AMSC) has turned into a favorable tool for large-scale multi-view clustering. However, there still exist some limitations to the current AMSC approaches. First, they typically recover anchor graph structure in the original linear space, restricting their feasibility for nonlinear scenarios. Second, they usually overlook the potential benefits of jointly capturing the inter-view and intra-view information for enhancing the anchor representation learning. Third, these approaches mostly perform anchor-based subspace learning by a specific matrix norm, neglecting the latent high-order correlation across different views. To overcome these limitations, this article presents an efficient and effective approach termed Large-Scale Tensorized Multi-View Kernel Subspace Clustering (LTKMSC). Different from the existing AMSC approaches, our LTKMSC approach exploits both inter-view and intra-view awareness for anchor-based representation building. Concretely, the low-rank tensor learning is leveraged to capture the high-order correlation (i.e., the inter-view complementary information) among distinct views, upon which the \(l_{1,2}\) norm is imposed to explore the intra-view anchor graph structure in each view. Moreover, the kernel learning technique is leveraged to explore the nonlinear anchor–sample relationships embedded in multiple views. With the unified objective function formulated, an efficient optimization algorithm that enjoys low computational complexity is further designed. Extensive experiments on a variety of multi-view datasets have confirmed the efficiency and effectiveness of our approach when compared with the other competitive approaches.- 22 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (4) , 1-21
Open AccessLarge-Scale Tensorized Multi-View Kernel Subspace Clustering
The anchor-based multi-view subspace clustering (AMSC) has turned into a favorable tool for large-scale multi-view clustering. However, there still exist some limitations to the current AMSC approaches. First, they typically recover anchor graph structure in the original linear space, restricting their feasibility for nonlinear scenarios. Second, they usually overlook the potential benefits of jointly capturing the inter-view and intra-view information for enhancing the anchor representation learning. Third, these approaches mostly perform anchor-based subspace learning by a specific matrix norm, neglecting the latent high-order correlation across different views. To overcome these limitations, this article presents an efficient and effective approach termed Large-Scale Tensorized Multi-View Kernel Subspace Clustering (LTKMSC). Different from the existing AMSC approaches, our LTKMSC approach exploits both inter-view and intra-view awareness for anchor-based representation building. Concretely, the low-rank tensor learning is leveraged to capture the high-order correlation (i.e., the inter-view complementary information) among distinct views, upon which the \(l_{1,2}\) norm is imposed to explore the intra-view anchor graph structure in each view. Moreover, the kernel learning technique is leveraged to explore the nonlinear anchor–sample relationships embedded in multiple views. With the unified objective function formulated, an efficient optimization algorithm that enjoys low computational complexity is further designed. Extensive experiments on a variety of multi-view datasets have confirmed the efficiency and effectiveness of our approach when compared with the other competitive approaches. - 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (4) , 2952-2964
Efficient Multi-View Clustering via Essential Tensorized Bipartite Graph Learning
Multi-view spectral clustering has garnered significant attention for its capacity to integrate intrinsic feature information from multiple perspectives, resulting in improved performance. However, the oversight of inter-view correlations has led to suboptimal outcomes. Furthermore, the conventional method of constructing an $N \times N$ graph in multi-view clustering imposes a substantial time burden when dealing with large-scale scenarios. To address these challenges, this paper presents an efficient multi-view clustering approach via Essential Tensorized Bipartite Graph Learning (ETBGL). Specifically, ETBGL utilizes the low-rank tensor Schatten $p$-norm to capture inter-view similarity, effectively capturing high-order correlation information embedded in multiple views. Simultaneously, by incorporating bipartite graph learning, ETBGL efficiently mitigates the computational demands and spatial complexity associated with tensor operations. Additionally, we introduce the $\ell _{2,1}$-norm of tensor as a sparse penalty to the error term, with the aim of filtering out noise and preserving shared information, thus enhancing clustering robustness. We solve our objective by an efficient algorithm that is time-economical and has good convergence. Comprehensive evaluations on diverse datasets demonstrate the exceptional performance of our proposed model.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (4) , 2952-2964
Efficient Multi-View Clustering via Essential Tensorized Bipartite Graph Learning
Multi-view spectral clustering has garnered significant attention for its capacity to integrate intrinsic feature information from multiple perspectives, resulting in improved performance. However, the oversight of inter-view correlations has led to suboptimal outcomes. Furthermore, the conventional method of constructing an $N \times N$ graph in multi-view clustering imposes a substantial time burden when dealing with large-scale scenarios. To address these challenges, this paper presents an efficient multi-view clustering approach via Essential Tensorized Bipartite Graph Learning (ETBGL). Specifically, ETBGL utilizes the low-rank tensor Schatten $p$-norm to capture inter-view similarity, effectively capturing high-order correlation information embedded in multiple views. Simultaneously, by incorporating bipartite graph learning, ETBGL efficiently mitigates the computational demands and spatial complexity associated with tensor operations. Additionally, we introduce the $\ell _{2,1}$-norm of tensor as a sparse penalty to the error term, with the aim of filtering out noise and preserving shared information, thus enhancing clustering robustness. We solve our objective by an efficient algorithm that is time-economical and has good convergence. Comprehensive evaluations on diverse datasets demonstrate the exceptional performance of our proposed model.
- 9 July 2024
- Published by Elsevier in Neural Networks
- Vol. 179, 106529
Tensorized Incomplete Multi-view Kernel Subspace Clustering
- 9 July 2024
- Published by Elsevier in Neural Networks
- Vol. 179, 106529
Tensorized Incomplete Multi-view Kernel Subspace Clustering
- 30 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 8 (2) , 1550-1566
Unified and Tensorized Incomplete Multi-View Kernel Subspace Clustering
Incomplete multi-view clustering (IMC) has recently received widespread attention in the field of clustering analysis. In spite of the great success, we observe that the current IMC approaches are still faced with three common demerits. First, they mostly fail to recover the inherent (especially nonlinear) subspace structure during incomplete clustering procedure. Second, these approaches tend to design the objective function by some specific matrix norms, yet often overlook the high-level correlation embedded in heterogeneous views. Third, many of them follow a two-stage framework, which inevitably leads to the sub-optimal clustering result due to the lack of the ability of joint optimization. To overcome these demerits, we develop a novel approach termed Unified and Tensorized Incomplete Multi-view Kernel Subspace Clustering (UT-IMKSC) in this paper. Specifically, a kernelized incomplete subspace clustering framework is formulated to exploit the inherent subspace structure from multiple views. In this framework, we aim to impute the incomplete kernels and perform incomplete subspace clustering simultaneously, upon which the low-rank tensor representations as well as their affinity matrix can be seamlessly achieved in a one-step manner. This unified formulation enables our approach to recover the latent relationship among observed and unobserved samples, while capturing the high-level correlation for strengthened subspace clustering. To the best of our knowledge, our approach is the first attempt to formulate incomplete multi-view kernel subspace clustering from unified and tensorized perspectives. Extensive experiments are conducted on various incomplete multi-view datasets, which have demonstrated the superiority of our approach over the state-of-the-art.
- 30 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 8 (2) , 1550-1566
Unified and Tensorized Incomplete Multi-View Kernel Subspace Clustering
Incomplete multi-view clustering (IMC) has recently received widespread attention in the field of clustering analysis. In spite of the great success, we observe that the current IMC approaches are still faced with three common demerits. First, they mostly fail to recover the inherent (especially nonlinear) subspace structure during incomplete clustering procedure. Second, these approaches tend to design the objective function by some specific matrix norms, yet often overlook the high-level correlation embedded in heterogeneous views. Third, many of them follow a two-stage framework, which inevitably leads to the sub-optimal clustering result due to the lack of the ability of joint optimization. To overcome these demerits, we develop a novel approach termed Unified and Tensorized Incomplete Multi-view Kernel Subspace Clustering (UT-IMKSC) in this paper. Specifically, a kernelized incomplete subspace clustering framework is formulated to exploit the inherent subspace structure from multiple views. In this framework, we aim to impute the incomplete kernels and perform incomplete subspace clustering simultaneously, upon which the low-rank tensor representations as well as their affinity matrix can be seamlessly achieved in a one-step manner. This unified formulation enables our approach to recover the latent relationship among observed and unobserved samples, while capturing the high-level correlation for strengthened subspace clustering. To the best of our knowledge, our approach is the first attempt to formulate incomplete multi-view kernel subspace clustering from unified and tensorized perspectives. Extensive experiments are conducted on various incomplete multi-view datasets, which have demonstrated the superiority of our approach over the state-of-the-art.
- Open Access
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction
In this paper, we present a novel deep image clustering approach termed PICI, which enforces the partial information discrimination and the cross-level interaction in a joint learning framework. In particular, we leverage a Transformer encoder as the backbone, through which the masked image modeling with two paralleled augmented views is formulated. After deriving the class tokens from the masked images by the Transformer encoder, three partial information learning modules are further incorporated, including the PISD module for training the auto-encoder via masked image reconstruction, the PICD module for employing two levels of contrastive learning, and the CLI module for mutual interaction between the instance-level and cluster-level subspaces. Extensive experiments have been conducted on six real-world image datasets, which demononstrate the superior clustering performance of the proposed PICI approach over the state-of-the-art deep clustering approaches. The source code is available at https://github.com/Regan-Zhang/PICI.
Open AccessLearning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction
In this paper, we present a novel deep image clustering approach termed PICI, which enforces the partial information discrimination and the cross-level interaction in a joint learning framework. In particular, we leverage a Transformer encoder as the backbone, through which the masked image modeling with two paralleled augmented views is formulated. After deriving the class tokens from the masked images by the Transformer encoder, three partial information learning modules are further incorporated, including the PISD module for training the auto-encoder via masked image reconstruction, the PICD module for employing two levels of contrastive learning, and the CLI module for mutual interaction between the instance-level and cluster-level subspaces. Extensive experiments have been conducted on six real-world image datasets, which demononstrate the superior clustering performance of the proposed PICI approach over the state-of-the-art deep clustering approaches. The source code is available at https://github.com/Regan-Zhang/PICI.
- 14 June 2023
- Published by Springer Nature in Soft Computing
- Vol. 28 (5) , 4321-4333
Motorcyclist helmet detection in single images: a dual-detection framework with multi-head self-attention
- 14 June 2023
- Published by Springer Nature in Soft Computing
- Vol. 28 (5) , 4321-4333
Motorcyclist helmet detection in single images: a dual-detection framework with multi-head self-attention
- Open Access
- 17 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 368-372
Deep Attributed Graph Clustering with Graph Attention Network
- 17 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 368-372
Open AccessDeep Attributed Graph Clustering with Graph Attention Network