Wei Zhang

Dr. Wei Zhang


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 June 2025 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
Hengrong JuHengrong Ju
Hengrong Ju
YLYang Lu
Yang Lu
Weiping DingWeiping Ding
Weiping Ding
Wei ZhangWei Zhang
Wei Zhang
Xibei YangXibei Yang
Xibei Yang
Contrastive multiview clustering (MVC) has emerged as a mainstream approach in MVC due to its superior representation learning capabilities. Traditional contrastive multiview learning methods extract both low- and high-level information from raw data. However, only high-level information is utilized for clustering. Since both types of information are essential for effective clustering, this limitation hampers performance. Moreover, effectively quantifying the importance of different views remains a critical challenge in contrastive MVC. Additionally, the absence of structural information during clustering further weakens clustering performance. To address these issues, this article proposes a multigranularity (MG) information fused contrastive learning with MVC (MGCMVC). Inspired by the concept of MG, low- and high-level features are reconstructed into fine- and coarse-granularity features. First, an MG adaptive weighting sample-level contrastive learning mechanism is introduced to fuse MG features to enhance clustering performance and mitigate clustering performance degradation caused by variations in view quality. Second, a structure-oriented cluster-level contrastive learning approach is designed to preserve structural information and enforce cross-view clustering consistency. Extensive and comprehensive experiments on ten widely used datasets demonstrate that MGCMVC achieves the state-of-the-art performance. The source code is available at https://github.com/Luyangabc/MGCMVC

1 November 2024 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
Wei ZhangWei Zhang
Wei Zhang
XHXiuyu Huang
Xiuyu Huang
ALAndong Li
Andong Li
TZTe Zhang
Te Zhang
Weiping DingWeiping Ding
Weiping Ding
SWShitong Wang
Shitong Wang
Multi-view anchor graph clustering has been a prominent research area in recent years, leading to the development of several effective and efficient methods. However, three challenges are faced by current multi-view anchor graph clustering methods. First, real-world data often exhibit uncertainty and poor discriminability, leading to suboptimal anchor graphs when directly extracted from the original data. Second, most existing methods assume the presence of common information between views and primarily explore it for clustering, thus neglecting view specific information. Third, further exploration and exploitation of the learned anchor graph to enhance clustering performance remains an open research question. To address these issues, a novel dual anchor graph fuzzy clustering method is proposed in this paper. First, a novel matrix factorization based dual anchor graph learning method is proposed to address the first two issues by extracting highly discriminative hidden representations for each view and subsequently deriving both common and specific anchor graphs from these hidden representations. Then, to address the third issue, a novel anchor graph fuzzy clustering method is developed with cooperative learning to exploit and utilize the common and specific anchor graphs fully. Meanwhile, a fuzzy membership structure preservation mechanism with dual anchor graphs is constructed to enhance clustering performance. Finally, negative Shannon entropy is further introduced to adaptively adjust the view weighing. Extensive experiments on several datasets demonstrate the effectiveness of the proposed method.

2 June 2025 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
YCYuepeng Chen
Yuepeng Chen
Weiping DingWeiping Ding
Weiping Ding
JHJiaShuang Huang
JiaShuang Huang
Wei ZhangWei Zhang
Wei Zhang
TZTianyi Zhou
Tianyi Zhou
Biological datasets, such as gene expression data, often suffer from high dimensionality, containing numerous irrelevant or redundant features that can lead to overfitting and increased computational complexity. Effective feature selection is essential for reducing dimensionality, enhancing model performance, and improving interpretability. While deep neural networks, such as autoencoders, have shown promise in feature selection, their performance often diminishes when confronted with noisy data. To address these challenges, we propose a novel feature selection method that leverages multigranularity fuzzy autoencoders (FAEs). This approach integrates fuzzy theory with autoencoder models to effectively manage noise and outliers in data. The FAE method introduces a feature selection layer that approximates discrete feature selection using continuous probability distributions. To further enhance the discriminative power of the selected features, we incorporate a coarse-grained loss function designed to exploit clustering structures. In addition, intuitionistic fuzzy weights are applied to account for uncertainty by computing membership and nonmembership degrees for each sample, thereby mitigating the impact of noise and outliers. Test results validate the effectiveness of our approach, demonstrating significant improvements over existing feature selection techniques across 20 public datasets and a real-world schizophrenia dataset. These findings highlight the potential of our method to enhance classification accuracy and robustness, particularly in the context of schizophrenia research.

1 August 2023 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
HYHongtan Yang
Hongtan Yang
ZDZhaohong Deng
Zhaohong Deng
Wei ZhangWei Zhang
Wei Zhang
QWQunzhuo Wu
Qunzhuo Wu
KCKup-Sze Choi
Kup-Sze Choi
SWShitong Wang
Shitong Wang
Multi-view clustering has received great attention in recent years for the potential in clustering performance improvement by using cooperative learning of different views. Despite the considerable progress, a few issues remain: (1) real multi-view data contains redundant features and noises that lead to unsatisfactory clustering performance; (2) most existing multi-view clustering methods only mine the shared information between views and ignore the specific information within views; (3) most multi-view clustering methods are based on a two-step framework that learn the hidden view representation and then perform clustering, overlooking the correlation between the two processes. Although some approaches have been proposed to deal with these issues, they cannot them simultaneously. To this end, we propose an end-to-end multi-view fuzzy clustering (EMVFC). First, we construct a multi-view fuzzy clustering framework to mine the specific information of the visible views. Second, to reduce the impact of redundant features and noises on clustering performance, we introduce the orthogonal projection matrix into the clustering framework to learn the low-dimensional representation of the visible views. Meanwhile, this procedure is integrated into the clustering framework. Third, we explore the shared hidden view representation between the visible views by multi-view non-negative matrix factorization and integrate it into the clustering framework to realize visible-hidden view cooperation learning. Finally, the shared hidden view representation learning between visible views, the low-dimensional representation learning of visible views, and the clustering partition of multi-view data negotiate with each other in the end-to-end learning framework. Extensive experiments on benchmark multi-view datasets indicate the superiority of the proposed method over state-of-the-art methods.

27 October 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ZZZiqi Zhang
Ziqi Zhang
ZDZhaohong Deng
Zhaohong Deng
Wei ZhangWei Zhang
Wei Zhang
LBLingchao Bu
Lingchao Bu
Spam detection has been a topic of extensive research; however, there has been limited focus on multimodal spam detection. In this study, we introduce a novel approach for multilingual multimodal spam detection, presenting the Multilingual and Multimodal Spam Detection Model combining Text and Document Images (MMTD). Unlike previous methods, our proposed model incorporates a document image encoder to extract image features from the entire email, providing a holistic understanding of both textual and visual content through a single image. Additionally, we employ a multilingual text encoder to extract textual features, enabling our model to process multilingual text content found in emails. To fuse the multimodal features, we employ a multimodal fusion module. Addressing the challenge of scarce large multilingual multimodal spam datasets, we introduce a new multilingual multimodal spam detection dataset comprising over 30,000 samples, which stands as the largest dataset of its kind to date. This dataset facilitates a rigorous evaluation of our proposed method. Extensive experiments were conducted on this dataset, and the performance of our model was validated using a five-fold cross-validation approach. The experimental results demonstrate the superiority of our approach, with our model achieving state-of-the-art performance, boasting an accuracy of 99.8% when compared to other advanced methods in the field.

24 September 2025 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
Wei ZhangWei Zhang
Wei Zhang
ZDZhaohong Deng
Zhaohong Deng
GWGuanjin Wang
Guanjin Wang
KCKup-Sze Choi
Kup-Sze Choi
Representation learning is a key area in machine learning and deep learning, focusing on extracting meaningful features to support downstream tasks such as classification and clustering. Current mainstream representation learning methods primarily rely on nonlinear data mining techniques such as kernel methods and deep neural networks (DNNs) to extract abstract knowledge from complex datasets. However, most of them are “black-box” methods, lacking transparency and interpretability in the learning process, which constrain their practical utility. To this end, this article introduces a novel representation learning method called fuzzy rule-based differentiable representation learning (FRDRL), which is grounded in an interpretable fuzzy rule-based model. Specifically, it is built upon the Takagi–Sugeno–Kang fuzzy system (TSK-FS) to map input data to a high-dimensional fuzzy feature space through the antecedent part of the TSK-FS. Subsequently, a novel differentiable optimization method is proposed for learning in the consequent part, which preserves interpretability and transparency while effectively capturing nonlinear relationships in the data. By retaining the essence of traditional optimization and parameterizing key components as differentiable modules, the method improves performance without sacrificing interpretability. Moreover, a second-order geometry preservation strategy is incorporated to further improve robustness. Extensive evaluations conducted on various benchmark datasets validate the superiority of the proposed method. The source codes are available at https://github.com/BBKing49/FEDRL