Zhenglai Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Zhenglai Li has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Chang Tang
Huazhong University of Science and Technology
19 shared publications - Xinwang Liu
National University of Defense Technology
16 shared publications - Wei Zhang
Qilu University of Technology (Shandong Academy of Sciences)
7 shared publications - Jun Wang
National University of Defense Technology
4 shared publications - En Zhu
National University of Defense Technology
3 shared publications - Xiao He
School of Computer Science, Wuhan University, Wuhan, China
3 shared publications
Latest Publications
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-16
Balanced Multi-view Clustering
Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC potentially does not fully leverage the multi-view information, due to the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, an analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches both on eight benchmark MvC datasets and two spatially resolved transcriptomics datasets. The demo code of this work is publicly available at https://github.com/guanyuezhen/BMvC.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-16
Balanced Multi-view Clustering
Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC potentially does not fully leverage the multi-view information, due to the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, an analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches both on eight benchmark MvC datasets and two spatially resolved transcriptomics datasets. The demo code of this work is publicly available at https://github.com/guanyuezhen/BMvC.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-16
Learning Disentangled Representations for Generalized Multi-view Clustering
Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view fusion, which hampers the quality of the shared latent space and leads to suboptimal clustering performance. To address this issue, we propose the Generalized Multi-view Auto-Encoder (GMAE), a framework designed to preserve cross-view complementarity through disentangled representation learning. Specifically, GMAE employs dual-path autoencoders to decouple source features into view-specific and view-common embeddings, facilitating the discovery of clearer clustering structures. We further construct cross-view adversarial discriminators to guide view-specific encoders in capturing more discriminative features. By strategically modulating mutual information, GMAE effectively aligns distributions and prevents representation collapse, ensuring the generation of robust, non-trivial embeddings. Comprehensive experiments on 13 benchmark datasets demonstrate that GMAE consistently outperforms state-of-the-art methods in both complete and incomplete MVC tasks. Our code implementation is available at the repository: https://github.com/obananas/GMAE.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP  (01628828) , 1-16
Learning Disentangled Representations for Generalized Multi-view Clustering
Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view fusion, which hampers the quality of the shared latent space and leads to suboptimal clustering performance. To address this issue, we propose the Generalized Multi-view Auto-Encoder (GMAE), a framework designed to preserve cross-view complementarity through disentangled representation learning. Specifically, GMAE employs dual-path autoencoders to decouple source features into view-specific and view-common embeddings, facilitating the discovery of clearer clustering structures. We further construct cross-view adversarial discriminators to guide view-specific encoders in capturing more discriminative features. By strategically modulating mutual information, GMAE effectively aligns distributions and prevents representation collapse, ensuring the generation of robust, non-trivial embeddings. Comprehensive experiments on 13 benchmark datasets demonstrate that GMAE consistently outperforms state-of-the-art methods in both complete and incomplete MVC tasks. Our code implementation is available at the repository: https://github.com/obananas/GMAE.
- Top Cited Papers
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. PP  (4) , 1-11
Spatially Resolved Transcriptomics Data Clustering With Modality Conflict Modulation
Spatial transcriptomics (ST) clustering identifies distinct spatial domains within tissues and elucidates cellular interactions. While this approach has advanced human understanding of cellular organization, ST data exhibit modality conflict between transcriptional profiles and spatial coordinates. This conflict manifests as spatial neighboring spots displaying expression divergence and presents fundamental challenges in defining cluster boundaries. To address this, we propose a spatially resolved transcriptomics data clustering network with modality conflict modulation(stMCM). Our framework is the first one that transforms cellular spatial coordinates into feature representations while introducing a novel cross-propagation architecture that propagates spatial and gene features through dual graph networks, thereby reinforcing consistency in domains where spatial and transcriptional patterns align. To specifically address spatial spurious correlations in cell pairs exhibiting expression divergence, we projected gene features onto a hypersphere to calculate similarity, followed by evaluation of spatially masked graph reconstruction likelihood using Jensen-Shannon Divergence (JSD). Extensive experimental results demonstrate that our approach surpasses existing state-of-the-art methods in clustering tasks and related downstream applications.
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. PP  (4) , 1-11
Top Cited PapersSpatially Resolved Transcriptomics Data Clustering With Modality Conflict Modulation
Spatial transcriptomics (ST) clustering identifies distinct spatial domains within tissues and elucidates cellular interactions. While this approach has advanced human understanding of cellular organization, ST data exhibit modality conflict between transcriptional profiles and spatial coordinates. This conflict manifests as spatial neighboring spots displaying expression divergence and presents fundamental challenges in defining cluster boundaries. To address this, we propose a spatially resolved transcriptomics data clustering network with modality conflict modulation(stMCM). Our framework is the first one that transforms cellular spatial coordinates into feature representations while introducing a novel cross-propagation architecture that propagates spatial and gene features through dual graph networks, thereby reinforcing consistency in domains where spatial and transcriptional patterns align. To specifically address spatial spurious correlations in cell pairs exhibiting expression divergence, we projected gene features onto a hypersphere to calculate similarity, followed by evaluation of spatially masked graph reconstruction likelihood using Jensen-Shannon Divergence (JSD). Extensive experimental results demonstrate that our approach surpasses existing state-of-the-art methods in clustering tasks and related downstream applications.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38  (3) , 2015-2027
Tensor Multi-Rank Constraint Guided Anchor-Wise Adaptive Alignment for Multi-View Clustering
Anchor graph learning has become a widely used technique for significantly reducing the computational complexity in existing multi-view clustering methods. However, most existing approaches select anchors independently for each view and then generate the consensus graph by directly fusing all anchor graphs. This process overlooks the correspondence between anchor sets across different views, i.e., the column order correspondence of the anchor graphs. To address this limitation, we propose a novel anchor-based tensor multi-rank constraint multi-view clustering method (TMC). Specifically, TMC captures the high-order structural information of the original data by constructing an anchor graph tensor and enforcing a multi-rank constraint to induce a block-diagonal structure. Additionally, to enhance anchor consistency across all view, we construct the anchor graph of each view into an anchor tensor and impose a low-rank constraint on it. In this way, the block-diagonal structure of each anchor graph maintains an approximate alignment between anchors. Furthermore, we provide theoretical proof that the generated anchor graphs inherently exhibit a block-diagonal structure. Extensive experimental results on six multi-view datasets demonstrate that TMC outperforms existing state-of-the-art methods, highlighting its effectiveness in multi-view clustering task.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38  (3) , 2015-2027
Tensor Multi-Rank Constraint Guided Anchor-Wise Adaptive Alignment for Multi-View Clustering
Anchor graph learning has become a widely used technique for significantly reducing the computational complexity in existing multi-view clustering methods. However, most existing approaches select anchors independently for each view and then generate the consensus graph by directly fusing all anchor graphs. This process overlooks the correspondence between anchor sets across different views, i.e., the column order correspondence of the anchor graphs. To address this limitation, we propose a novel anchor-based tensor multi-rank constraint multi-view clustering method (TMC). Specifically, TMC captures the high-order structural information of the original data by constructing an anchor graph tensor and enforcing a multi-rank constraint to induce a block-diagonal structure. Additionally, to enhance anchor consistency across all view, we construct the anchor graph of each view into an anchor tensor and impose a low-rank constraint on it. In this way, the block-diagonal structure of each anchor graph maintains an approximate alignment between anchors. Furthermore, we provide theoretical proof that the generated anchor graphs inherently exhibit a block-diagonal structure. Extensive experimental results on six multi-view datasets demonstrate that TMC outperforms existing state-of-the-art methods, highlighting its effectiveness in multi-view clustering task.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-12
Boosting Remote Sensing Change Detection via Hard Region Mining
Change detection (CD) is essential for various real-world applications, such as urban management and disaster assessment. Numerous CD methods have been proposed, and considerable results have been achieved recently. However, detecting changes in hard regions, for example, the boundaries of changes, small changes, and irrelevant pseudo-changes caused by background clutter, remains difficult for these methods, since they pay equal attention to all regions in bi-temporal images. This article proposes a novel CD network, termed HRMNet, which provides accurate change maps via hard region mining. Specifically, the HRMNet performs hard region mining from two different perspectives: 1) a cross-layer knowledge review module (CKRM) is introduced to identify hard regions embedded in high-level features and distill temporal change information from low-level features to high-level features, thereby enhancing feature representation capabilities and 2) an online hard region estimation (OHRE) branch is constructed to model pixel-wise hard samples, supervised by the error between predicted change maps and the corresponding ground truth during training. Finally, the hard region-aware features extracted from the OHRE branch and multilevel temporal difference features are aggregated into a unified feature representation to improve the accuracy of CD. Experimental results on three benchmark datasets demonstrate the superior performance of the HRMNet in the CD task. The demo code for our work is publicly available at https://github.com/guanyuezhen/HRMNet
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-12
Boosting Remote Sensing Change Detection via Hard Region Mining
Change detection (CD) is essential for various real-world applications, such as urban management and disaster assessment. Numerous CD methods have been proposed, and considerable results have been achieved recently. However, detecting changes in hard regions, for example, the boundaries of changes, small changes, and irrelevant pseudo-changes caused by background clutter, remains difficult for these methods, since they pay equal attention to all regions in bi-temporal images. This article proposes a novel CD network, termed HRMNet, which provides accurate change maps via hard region mining. Specifically, the HRMNet performs hard region mining from two different perspectives: 1) a cross-layer knowledge review module (CKRM) is introduced to identify hard regions embedded in high-level features and distill temporal change information from low-level features to high-level features, thereby enhancing feature representation capabilities and 2) an online hard region estimation (OHRE) branch is constructed to model pixel-wise hard samples, supervised by the error between predicted change maps and the corresponding ground truth during training. Finally, the hard region-aware features extracted from the OHRE branch and multilevel temporal difference features are aggregated into a unified feature representation to improve the accuracy of CD. Experimental results on three benchmark datasets demonstrate the superior performance of the HRMNet in the CD task. The demo code for our work is publicly available at https://github.com/guanyuezhen/HRMNet
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35  (12) , 11822-11833
Mask-Informed Deep Contrastive Incomplete Multi-View Clustering
Multi-view clustering (MvC) utilizes information from multiple views to uncover the underlying structures of data. Despite significant advancements in MvC, mitigating the impact of missing samples in specific views on the integration of knowledge from different views remains a critical challenge. This paper proposes a novel Mask-informed Deep Contrastive Incomplete Multi-view Clustering (Mask-IMvC) method, which elegantly identifies a view-common representation for clustering. Specifically, we introduce a mask-informed fusion network that aggregates incomplete multi-view information while considering the observation status of samples across various views as a mask, thereby reducing the adverse effects of missing values. Additionally, we design a prior knowledge-assisted contrastive learning loss that boosts the representation capability of the aggregated view-common representation by injecting neighborhood information of samples from different views. Finally, extensive experiments are conducted to demonstrate the superiority of the proposed Mask-IMvC method over state-of-the-art approaches across multiple MvC datasets, both in complete and incomplete scenarios. The demo code for our work will be publicly available at https://github.com/guanyuezhen/Mask-IMvC.
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35  (12) , 11822-11833
Mask-Informed Deep Contrastive Incomplete Multi-View Clustering
Multi-view clustering (MvC) utilizes information from multiple views to uncover the underlying structures of data. Despite significant advancements in MvC, mitigating the impact of missing samples in specific views on the integration of knowledge from different views remains a critical challenge. This paper proposes a novel Mask-informed Deep Contrastive Incomplete Multi-view Clustering (Mask-IMvC) method, which elegantly identifies a view-common representation for clustering. Specifically, we introduce a mask-informed fusion network that aggregates incomplete multi-view information while considering the observation status of samples across various views as a mask, thereby reducing the adverse effects of missing values. Additionally, we design a prior knowledge-assisted contrastive learning loss that boosts the representation capability of the aggregated view-common representation by injecting neighborhood information of samples from different views. Finally, extensive experiments are conducted to demonstrate the superiority of the proposed Mask-IMvC method over state-of-the-art approaches across multiple MvC datasets, both in complete and incomplete scenarios. The demo code for our work will be publicly available at https://github.com/guanyuezhen/Mask-IMvC.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8287-8295
Heterogeneous Graph Guided Contrastive Learning for Spatially Resolved Transcriptomics Data
Spatial transcriptomics provides revolutionary insights into cellular interactions and disease development mechanisms by combining high-throughput gene sequencing and spatially resolved imaging technologies to analyze genes naturally associated with spatially variable tissue genes. However, existing methods typically map aggregated multi-view features into a unified representation, ignoring the heterogeneity and view independence of genes and spatial information. To this end, we construct a heterogeneous Graph guided Contrastive Learning (stGCL) for aggregating spatial transcriptomics data. The method is guided by the inherent heterogeneity of cellular molecules by dynamically coordinating triple-level node attributes through comparative learning loss distributed across view domains, thus maintaining view independence during the aggregation process. In addition, we introduce a cross-view hierarchical feature alignment module employing a parallel approach to decouple spatial and genetic views on molecular structures while aggregating multi-view features according to information theory, thereby enhancing the integrity of inter- and intra-views. Rigorous experiments demonstrate that stGCL outperforms existing methods in various tasks and related downstream applications.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8287-8295
Open AccessHeterogeneous Graph Guided Contrastive Learning for Spatially Resolved Transcriptomics Data
Spatial transcriptomics provides revolutionary insights into cellular interactions and disease development mechanisms by combining high-throughput gene sequencing and spatially resolved imaging technologies to analyze genes naturally associated with spatially variable tissue genes. However, existing methods typically map aggregated multi-view features into a unified representation, ignoring the heterogeneity and view independence of genes and spatial information. To this end, we construct a heterogeneous Graph guided Contrastive Learning (stGCL) for aggregating spatial transcriptomics data. The method is guided by the inherent heterogeneity of cellular molecules by dynamically coordinating triple-level node attributes through comparative learning loss distributed across view domains, thus maintaining view independence during the aggregation process. In addition, we introduce a cross-view hierarchical feature alignment module employing a parallel approach to decouple spatial and genetic views on molecular structures while aggregating multi-view features according to information theory, thereby enhancing the integrity of inter- and intra-views. Rigorous experiments demonstrate that stGCL outperforms existing methods in various tasks and related downstream applications.
- 20 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62  (01962892) , 1-13
MS-Former: Memory-Supported Transformer for Weakly Supervised Change Detection With Patch-Level Annotations
Fully supervised change detection (CD) methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information corresponding to both changed and unchanged objects in bi-temporal images, an intuitive solution is to segment the changes with patch-level annotations. How to capture the semantic variations associated with the changed and unchanged regions from the patch-level annotations to obtain promising change results is the critical challenge for the weakly supervised CD task. In this article, we propose a memory-supported transformer (MS-Former), a novel framework consisting of a bi-directional attention block (BAB) and a patch-level supervision scheme (PSS) tailored for weakly supervised CD with patch-level annotations. More specifically, the BAB captures contexts associated with the changed and unchanged regions from the temporal difference features to construct informative prototypes stored in the memory bank. On the other hand, the BAB extracts useful information from the prototypes as supplementary contexts to enhance the temporal difference features, thereby better distinguishing changed and unchanged regions. After that, the PSS guides the network learning valuable knowledge from the patch-level annotations, thus further elevating the performance. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method in the CD task. The demo code for our work will be publicly available at https://github.com/guanyuezhen/MS-Former .
- 20 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62  (01962892) , 1-13
MS-Former: Memory-Supported Transformer for Weakly Supervised Change Detection With Patch-Level Annotations
Fully supervised change detection (CD) methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information corresponding to both changed and unchanged objects in bi-temporal images, an intuitive solution is to segment the changes with patch-level annotations. How to capture the semantic variations associated with the changed and unchanged regions from the patch-level annotations to obtain promising change results is the critical challenge for the weakly supervised CD task. In this article, we propose a memory-supported transformer (MS-Former), a novel framework consisting of a bi-directional attention block (BAB) and a patch-level supervision scheme (PSS) tailored for weakly supervised CD with patch-level annotations. More specifically, the BAB captures contexts associated with the changed and unchanged regions from the temporal difference features to construct informative prototypes stored in the memory bank. On the other hand, the BAB extracts useful information from the prototypes as supplementary contexts to enhance the temporal difference features, thereby better distinguishing changed and unchanged regions. After that, the PSS guides the network learning valuable knowledge from the patch-level annotations, thus further elevating the performance. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method in the CD task. The demo code for our work will be publicly available at https://github.com/guanyuezhen/MS-Former .
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36  (11) , 6641-6652
Multiple Kernel Clustering With Adaptive Multi-Scale Partition Selection
Multiple kernel clustering (MKC) enhances clustering performance by deriving a consensus partition or graph from a predefined set of kernels. Despite many advanced MKC methods proposed in recent years, the prevalent approaches involve incorporating all kernels by default to capture diverse information within the data. However, learning from all kernels may not be better than one of a few kernels, particularly since some kernels exhibit a higher proportion of noise than semantic content. Additionally, existing MKC methods, whether based on early-fusion or late-fusion approaches, predominantly rely on pairwise relationships among samples or cluster structures, neglecting potential correlations between these two aspects. To this end, we propose a multiple kernel clustering with an adaptive multi-scale partition selection method (MPS), which exploits multiple-dimensional representations and the pairwise cluster structure for clustering. By the proposed kernel selection framework, potentially harmful kernels are dynamically excluded during the kernel fusion process, and then the multi-scale partitions and similarity graphs derived from the retained kernels are utilized to facilitate the improved consensus partition generation. Finally, extensive experiments are conducted to demonstrate the effectiveness of MPS on eight benchmark datasets.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36  (11) , 6641-6652
Multiple Kernel Clustering With Adaptive Multi-Scale Partition Selection
Multiple kernel clustering (MKC) enhances clustering performance by deriving a consensus partition or graph from a predefined set of kernels. Despite many advanced MKC methods proposed in recent years, the prevalent approaches involve incorporating all kernels by default to capture diverse information within the data. However, learning from all kernels may not be better than one of a few kernels, particularly since some kernels exhibit a higher proportion of noise than semantic content. Additionally, existing MKC methods, whether based on early-fusion or late-fusion approaches, predominantly rely on pairwise relationships among samples or cluster structures, neglecting potential correlations between these two aspects. To this end, we propose a multiple kernel clustering with an adaptive multi-scale partition selection method (MPS), which exploits multiple-dimensional representations and the pairwise cluster structure for clustering. By the proposed kernel selection framework, potentially harmful kernels are dynamically excluded during the kernel fusion process, and then the multi-scale partitions and similarity graphs derived from the retained kernels are utilized to facilitate the improved consensus partition generation. Finally, extensive experiments are conducted to demonstrate the effectiveness of MPS on eight benchmark datasets.