Zhu Chen
Research Subjects
Research Interests
Zhu Chen has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Jun Tan
School of Computer Science and Engineering, Central South University, Changsha 410083, China
1 shared publication - Ning Gui
School of Computer Science and engineering, Central South University, Changsha, China
1 shared publication - Wei Jiang
School of Computer Science and Engineering, Central South University, Changsha 410083, China
1 shared publication - Zhiqiang Li
Software Engineering Institute, East China Normal University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 18 November 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (22) , 3703
Supervised Feature Selection Method Using Stackable Attention Networks
Mainstream DNN-based feature selection methods share a similar design strategy: employing one specially designed feature selection module to learn the importance of features along with the model-training process. While these works achieve great success in feature selection, their shallow structures, which evaluate feature importance from one perspective, are easily disturbed by noisy samples, especially in datasets with high-dimensional features and complex structures. To alleviate this limitation, this paper innovatively introduces a Stackable Attention architecture for Feature Selection (SAFS), which can calculate stable and accurate feature weights through a set of Stackable Attention Blocks (SABlocks) rather than from a single module. To avoid information loss from stacking, a feature jump concatenation structure is designed. Furthermore, an inertia-based weight update method is proposed to generate a more robust feature weight distribution. Experiments on twelve real-world datasets, including multiple domains, demonstrate that SAFS produced the best results with significant performance edges compared to thirteen baselines.
- 18 November 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (22) , 3703
Open AccessSupervised Feature Selection Method Using Stackable Attention Networks
Mainstream DNN-based feature selection methods share a similar design strategy: employing one specially designed feature selection module to learn the importance of features along with the model-training process. While these works achieve great success in feature selection, their shallow structures, which evaluate feature importance from one perspective, are easily disturbed by noisy samples, especially in datasets with high-dimensional features and complex structures. To alleviate this limitation, this paper innovatively introduces a Stackable Attention architecture for Feature Selection (SAFS), which can calculate stable and accurate feature weights through a set of Stackable Attention Blocks (SABlocks) rather than from a single module. To avoid information loss from stacking, a feature jump concatenation structure is designed. Furthermore, an inertia-based weight update method is proposed to generate a more robust feature weight distribution. Experiments on twelve real-world datasets, including multiple domains, demonstrate that SAFS produced the best results with significant performance edges compared to thirteen baselines.