Weijie Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Weijie Chen has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Fei Cai
National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, China
2 shared publications - Xin Zhang
National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, China
2 shared publications - Yuzhuo Dang
National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, China
2 shared publications Zhiqiang Pan
2 shared publicationsBin Yan
1 shared publicationChaohua Wang
1 shared publication
Latest Publications
- 2 November 2026
- Published by Elsevier in Neural Networks
A Survey of Sparse Attention in Vision Transformers: Taxonomy, Methods and Analysis
- 2 November 2026
- Published by Elsevier in Neural Networks
A Survey of Sparse Attention in Vision Transformers: Taxonomy, Methods and Analysis
- Open Access
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 703-708
PCA–K-Means–Random Forest–Based Analysis of AI Empowerment in Higher Education: Paradigm Shifts and Implementation Strategies
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 703-708
Open AccessPCA–K-Means–Random Forest–Based Analysis of AI Empowerment in Higher Education: Paradigm Shifts and Implementation Strategies
- Open Access
A Multimodal Semantic-Enhanced Attention Network for Fake News Detection
The proliferation of social media platforms has triggered an unprecedented increase in multimodal fake news, creating pressing challenges for content authenticity verification. Current fake news detection systems predominantly rely on isolated unimodal analysis (text or image), failing to exploit critical cross-modal correlations or leverage latent social context cues. To bridge this gap, we introduce the SCCN (Semantic-enhanced Cross-modal Co-attention Network), a novel framework that synergistically combines multimodal features with refined social graph signals. Our approach innovatively combines text, image, and social relation features through a hierarchical fusion framework. First, we extract modality-specific features and enhance semantics by identifying entities in both text and visual data. Second, an improved co-attention mechanism selectively integrates social relations while removing irrelevant connections to reduce noise and exploring latent informative links. Finally, the model is optimized via cross-entropy loss with entropy minimization. Experimental results for benchmark datasets (PHEME and Weibo) show that SCCN consistently outperforms existing approaches, achieving relative accuracy enhancements of 1.7% and 1.6% over the best-performing baseline methods in each dataset.
Open AccessA Multimodal Semantic-Enhanced Attention Network for Fake News Detection
The proliferation of social media platforms has triggered an unprecedented increase in multimodal fake news, creating pressing challenges for content authenticity verification. Current fake news detection systems predominantly rely on isolated unimodal analysis (text or image), failing to exploit critical cross-modal correlations or leverage latent social context cues. To bridge this gap, we introduce the SCCN (Semantic-enhanced Cross-modal Co-attention Network), a novel framework that synergistically combines multimodal features with refined social graph signals. Our approach innovatively combines text, image, and social relation features through a hierarchical fusion framework. First, we extract modality-specific features and enhance semantics by identifying entities in both text and visual data. Second, an improved co-attention mechanism selectively integrates social relations while removing irrelevant connections to reduce noise and exploring latent informative links. Finally, the model is optimized via cross-entropy loss with entropy minimization. Experimental results for benchmark datasets (PHEME and Weibo) show that SCCN consistently outperforms existing approaches, achieving relative accuracy enhancements of 1.7% and 1.6% over the best-performing baseline methods in each dataset.
- 13 June 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 324
A Structure-Feature Dynamic Decoupling GNN architecture for link prediction
- 13 June 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 324
A Structure-Feature Dynamic Decoupling GNN architecture for link prediction
- Open Access
- 22 May 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (7) , 1-15
Contrastive learning of cross-modal information enhancement for multimodal fake news detection
- 22 May 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (7) , 1-15
Open AccessContrastive learning of cross-modal information enhancement for multimodal fake news detection
- Open Access
- 27 November 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (23) , 4780
REKP: Refined External Knowledge into Prompt-Tuning for Few-Shot Text Classification
Text classification is a machine learning technique employed to assign a given text to predefined categories, facilitating the automatic analysis and processing of textual data. However, an important problem is that the number of new text categories is growing faster than that of human annotation data, which makes many new categories of text data lack a lot of annotation data. As a result, the conventional deep neural network is forced to over-fit, which damages the application in the real world. As a solution to this problem, academics recommend addressing data scarcity through few-shot learning. One of the efficient methods is prompt-tuning, which transforms the input text into a mask prediction problem featuring [MASK]. By utilizing descriptors, the model maps output words to labels, enabling accurate prediction. Nevertheless, the previous prompt-based adaption approaches often relied on manually produced verbalizers or a single label to represent the entire label vocabulary, which makes the mapping granularity low, resulting in words not being accurately mapped to their label. To address these issues, we propose to enhance the verbalizer and construct the refined external knowledge into a prompt-tuning (REKP) model. We employ the external knowledge bases to increase the mapping space of tagged terms and design three refinement methods to remove noise data. We conduct comprehensive experiments on four benchmark datasets, namely AG’s News, Yahoo, IMDB, and Amazon. The results demonstrate that REKP can outperform the state-of-the-art baselines in terms of Micro-F1 on knowledge-enhanced text classification. In addition, we conduct an ablation study to ascertain the functionality of each module in our model, revealing that the refinement module significantly contributes to enhancing classification accuracy.
- 27 November 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (23) , 4780
Open AccessREKP: Refined External Knowledge into Prompt-Tuning for Few-Shot Text Classification
Text classification is a machine learning technique employed to assign a given text to predefined categories, facilitating the automatic analysis and processing of textual data. However, an important problem is that the number of new text categories is growing faster than that of human annotation data, which makes many new categories of text data lack a lot of annotation data. As a result, the conventional deep neural network is forced to over-fit, which damages the application in the real world. As a solution to this problem, academics recommend addressing data scarcity through few-shot learning. One of the efficient methods is prompt-tuning, which transforms the input text into a mask prediction problem featuring [MASK]. By utilizing descriptors, the model maps output words to labels, enabling accurate prediction. Nevertheless, the previous prompt-based adaption approaches often relied on manually produced verbalizers or a single label to represent the entire label vocabulary, which makes the mapping granularity low, resulting in words not being accurately mapped to their label. To address these issues, we propose to enhance the verbalizer and construct the refined external knowledge into a prompt-tuning (REKP) model. We employ the external knowledge bases to increase the mapping space of tagged terms and design three refinement methods to remove noise data. We conduct comprehensive experiments on four benchmark datasets, namely AG’s News, Yahoo, IMDB, and Amazon. The results demonstrate that REKP can outperform the state-of-the-art baselines in terms of Micro-F1 on knowledge-enhanced text classification. In addition, we conduct an ablation study to ascertain the functionality of each module in our model, revealing that the refinement module significantly contributes to enhancing classification accuracy.