Wenzhu Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wenzhu Yan has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Yanmeng Li
School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China
3 shared publications- Yanmeng Li
Nanjing University of Posts and Telecommunications
2 shared publications Jianqiu Li
School of Computer and Electronic Information, Nanjing Normal University, Nanjing, China
1 shared publicationJiayi Yao
School of Computer and Electronic Information, Nanjing Normal University, Nanjing, China
1 shared publication- Lei Wang
University of Wollongong, Wollongong, Australia
1 shared publication - Like Xin
School of Mathematical Sciences, Nanjing Normal University, Nanjing, China
1 shared publication
Latest Publications
- Open Access
- 11 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3127
Dual-Space Knowledge Distillation with Cross-Geometric Feature Interaction for Hyperspectral Image Classification
Hyperspectral image (HSI) classification is critical for remote sensing but faces challenges in balancing accuracy and inference efficiency. Existing graph-based knowledge distillation (KD) methods are confined to single geometric spaces, ignoring the hierarchical semantics of land-cover categories. Cross-geometry distillation compresses multiple geometries into a single Euclidean student, forcing one geometry to collapse into the other. In this paper, we propose Dual-Space Knowledge Distillation (DSKD), a novel dual-student dual-space KD framework integrating Euclidean (GCN) and Hyperbolic (HGCN) teachers to jointly train a native MLP student and a native HNN student. With cross-geometric feature bridging (CGFB) and output distribution cohesion (ODC), the two students mutually learn each other’s complementary geometry, so DSKD captures complementary spatial-spectral and hierarchical features while enabling graph-free inference without message passing. Extensive experiments on four HSI datasets and four general graph benchmarks demonstrate that DSKD outperforms single-space distillation and single-student cross-geometry baselines in most settings, confirming its effectiveness and generalization capability across diverse graph-structured data.
- 11 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3127
Open AccessDual-Space Knowledge Distillation with Cross-Geometric Feature Interaction for Hyperspectral Image Classification
Hyperspectral image (HSI) classification is critical for remote sensing but faces challenges in balancing accuracy and inference efficiency. Existing graph-based knowledge distillation (KD) methods are confined to single geometric spaces, ignoring the hierarchical semantics of land-cover categories. Cross-geometry distillation compresses multiple geometries into a single Euclidean student, forcing one geometry to collapse into the other. In this paper, we propose Dual-Space Knowledge Distillation (DSKD), a novel dual-student dual-space KD framework integrating Euclidean (GCN) and Hyperbolic (HGCN) teachers to jointly train a native MLP student and a native HNN student. With cross-geometric feature bridging (CGFB) and output distribution cohesion (ODC), the two students mutually learn each other’s complementary geometry, so DSKD captures complementary spatial-spectral and hierarchical features while enabling graph-free inference without message passing. Extensive experiments on four HSI datasets and four general graph benchmarks demonstrate that DSKD outperforms single-space distillation and single-student cross-geometry baselines in most settings, confirming its effectiveness and generalization capability across diverse graph-structured data.
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 3016-3028
Probabilistic Interpretation Toward Manifold Convex Hull Collaborative Representation
Convex Hull Representation and Learning (CHRL) has drawn great attention for set oriented data analysis. The traditional methods focus on representing set samples in a linear/affine feature space, which can be regarded as a convex geometric region spanned by its feature points. However, the non-Euclidean structure originating from these data is largely ignored by previous CHRLs. To deal with this problem, we propose a new Manifold Convex Hull Collaborative Representation (MCHCR) framework from geometry-aware perspective. Notably, we establish convex hull for Grassmann manifold points modeled by image sets, and then fully exploit the relationships between different sets by collaborative representation mechanism with a closed form solution. Our method definitely inherits the rich representability of Grassmann manifold and high flexibility of convex hull model. Moreover, we interpret the intrinsic classification mechanism of MCHCR under a solid theoretical analysis from probability perspective. Finally, the effectiveness of the proposed learning framework is effectively demonstrated on various benchmark datasets.
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 3016-3028
Probabilistic Interpretation Toward Manifold Convex Hull Collaborative Representation
Convex Hull Representation and Learning (CHRL) has drawn great attention for set oriented data analysis. The traditional methods focus on representing set samples in a linear/affine feature space, which can be regarded as a convex geometric region spanned by its feature points. However, the non-Euclidean structure originating from these data is largely ignored by previous CHRLs. To deal with this problem, we propose a new Manifold Convex Hull Collaborative Representation (MCHCR) framework from geometry-aware perspective. Notably, we establish convex hull for Grassmann manifold points modeled by image sets, and then fully exploit the relationships between different sets by collaborative representation mechanism with a closed form solution. Our method definitely inherits the rich representability of Grassmann manifold and high flexibility of convex hull model. Moreover, we interpret the intrinsic classification mechanism of MCHCR under a solid theoretical analysis from probability perspective. Finally, the effectiveness of the proposed learning framework is effectively demonstrated on various benchmark datasets.
- 5 May 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (3) , 1-14
Multiple kernel subspace representation and graph construction learning for multi-view clustering
- 5 May 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (3) , 1-14
Multiple kernel subspace representation and graph construction learning for multi-view clustering
- 20 October 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (6) , 1-16
Robust Grassmann manifold convex hull collaborative representation learning and its kernel extension for image set analysis
- 20 October 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (6) , 1-16
Robust Grassmann manifold convex hull collaborative representation learning and its kernel extension for image set analysis
- 24 December 2023
- Published by Springer Nature
- p. 453-465
Convex Hull Collaborative Representation Learning on Grassmann Manifold with $L_1$ Norm Regularization- 24 December 2023
- Published by Springer Nature
- p. 453-465
Convex Hull Collaborative Representation Learning on Grassmann Manifold with $L_1$ Norm Regularization- 15 December 2023
- Published by Springer Nature
- p. 125-135
Twin Support Vector Regression with Privileged Information
- 15 December 2023
- Published by Springer Nature
- p. 125-135
Twin Support Vector Regression with Privileged Information
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (10) , 14848-14862
Iterative Multiview Subspace Learning for Unpaired Multiview Clustering
In real applications, several unpredictable or uncertain factors could result in unpaired multiview data, i.e., the observed samples between views cannot be matched. Since joint clustering among views is more effective than individual clustering in each view, we investigate unpaired multiview clustering (UMC), which is a valuable but insufficiently studied problem. Due to lack of matched samples between views, we could fail to build the connection between views. Therefore, we aim to learn the latent subspace shared by views. However, existing multiview subspace learning methods usually rely on the matched samples between views. To address this issue, we propose an iterative multiview subspace learning strategy iterative unpaired multiview clustering (IUMC), aiming to learn a complete and consistent subspace representation among views for UMC. Moreover, based on IUMC, we design two effective UMC methods: 1) Iterative unpaired multiview clustering via covariance matrix alignment (IUMC-CA) that further aligns the covariance matrix of subspace representations and then performs clustering on the subspace and 2) iterative unpaired multiview clustering via one-stage clustering assignments (IUMC-CY) that performs one-stage multiview clustering (MVC) by replacing the subspace representations with clustering assignments. Extensive experiments show the excellent performance of our methods for UMC, compared with the state-of-the-art methods. Also, the clustering performance of observed samples in each view can be considerably improved by those observed samples from the other views. In addition, our methods have good applicability in incomplete MVC.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (10) , 14848-14862
Iterative Multiview Subspace Learning for Unpaired Multiview Clustering
In real applications, several unpredictable or uncertain factors could result in unpaired multiview data, i.e., the observed samples between views cannot be matched. Since joint clustering among views is more effective than individual clustering in each view, we investigate unpaired multiview clustering (UMC), which is a valuable but insufficiently studied problem. Due to lack of matched samples between views, we could fail to build the connection between views. Therefore, we aim to learn the latent subspace shared by views. However, existing multiview subspace learning methods usually rely on the matched samples between views. To address this issue, we propose an iterative multiview subspace learning strategy iterative unpaired multiview clustering (IUMC), aiming to learn a complete and consistent subspace representation among views for UMC. Moreover, based on IUMC, we design two effective UMC methods: 1) Iterative unpaired multiview clustering via covariance matrix alignment (IUMC-CA) that further aligns the covariance matrix of subspace representations and then performs clustering on the subspace and 2) iterative unpaired multiview clustering via one-stage clustering assignments (IUMC-CY) that performs one-stage multiview clustering (MVC) by replacing the subspace representations with clustering assignments. Extensive experiments show the excellent performance of our methods for UMC, compared with the state-of-the-art methods. Also, the clustering performance of observed samples in each view can be considerably improved by those observed samples from the other views. In addition, our methods have good applicability in incomplete MVC.
- 26 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (1) , 1-15
Robust Low Rank and Sparse Representation for Multiple Kernel Dimensionality Reduction
In the fields of pattern recognition and data mining, two problems need to be addressed. First, the curse of dimensionality degrades the performance of many practical data processing techniques. Second, due to the existence of noise and outliers, feature extraction on corrupted data can not be effectively achieved. Recently, some representation based methods have produced promising results. However, these methods cannot handle the case in which nonlinear similarity exists and have failed to provide the quantized interpretability for the importance of features. In this paper, we propose a novel low rank and sparse representation method to realize dimensionality reduction and robustly extract latent low dimensional discriminative features. Specifically, we first adopt multiple kernel learning to map the original data into an embedded reproducing kernel Hilbert space (RKHS) and then kernel based similarity discriminative projection is learned to explore the within-class and between-class variability. Notably, this low dimensional feature learning strategy is definitely integrated into the low rank matrix recovery of the kernel matrix. Next, we introduce the regularization of l2;1 norm on error matrix to eliminate noise and on projection matrix to lead the selected features to be more compact and interpretable. The non-convex optimization problem is effectively solved by the alternating direction method of multipliers (ADM-M) methods. Extensive experiments on seven benchmark datasets are conducted to demonstrate the effectiveness of our method.
- 26 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (1) , 1-15
Robust Low Rank and Sparse Representation for Multiple Kernel Dimensionality Reduction
In the fields of pattern recognition and data mining, two problems need to be addressed. First, the curse of dimensionality degrades the performance of many practical data processing techniques. Second, due to the existence of noise and outliers, feature extraction on corrupted data can not be effectively achieved. Recently, some representation based methods have produced promising results. However, these methods cannot handle the case in which nonlinear similarity exists and have failed to provide the quantized interpretability for the importance of features. In this paper, we propose a novel low rank and sparse representation method to realize dimensionality reduction and robustly extract latent low dimensional discriminative features. Specifically, we first adopt multiple kernel learning to map the original data into an embedded reproducing kernel Hilbert space (RKHS) and then kernel based similarity discriminative projection is learned to explore the within-class and between-class variability. Notably, this low dimensional feature learning strategy is definitely integrated into the low rank matrix recovery of the kernel matrix. Next, we introduce the regularization of l2;1 norm on error matrix to eliminate noise and on projection matrix to lead the selected features to be more compact and interpretable. The non-convex optimization problem is effectively solved by the alternating direction method of multipliers (ADM-M) methods. Extensive experiments on seven benchmark datasets are conducted to demonstrate the effectiveness of our method.