Da Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Da Wang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Lin Li
Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, Shanxi, China
2 shared publications - Wei Wei
Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, Shanxi, China
2 shared publications - Dongyu Pei
North University of China, Taiyuan, China
1 shared publication - Gangzhu Qiao
North University of China, Taiyuan, China
1 shared publication - Huizhong Song
Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, Shanxi, China
1 shared publication - Jiye Liang
Shanxi University
1 shared publication
Latest Publications
- 15 October 2026
- Published by Elsevier in Neural Networks
- Vol. 206 (Pt A) , 109769
Structured goal-guided reinforcement learning with large language models
- 15 October 2026
- Published by Elsevier in Neural Networks
- Vol. 206 (Pt A) , 109769
Structured goal-guided reinforcement learning with large language models
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 959-967
PAGE: Progressive Anomaly Generation Network for Semi-supervised Graph Anomaly Detection
Semi-supervised graph anomaly detection confronts the fundamental challenge of identifying anomalous nodes that exhibit deviations from normal graph patterns in node attributes or structure connectivity, using a small set of labeled normal nodes. Existing methods fall short in modeling the spectrum of anomaly severity, as they generate anomalies in a single, undifferentiated step. This oversight restricts the detection of complex anomalies. In this paper, we propose a progressive anomaly generation network (PAGE) to overcome this limitation. PAGE enhances complex anomaly detection through progressive attribute-structure perturbation: It first injects attribute noise into selected normal nodes to generate pseudo-anomalous nodes. Then it applies progressive structure perturbation to create hybrid anomalies that simulate the evolution from mild to complex perturbations. Importantly, the proposed anomaly progressive constraint loss enforces that hybrid anomalies exhibit a higher degree of abnormality than primary anomalies, enhancing the model's anomaly quantification capability. PAGE further integrates deviation constraint loss and classification loss to optimize node representations and improve prediction. Extensive experiments on benchmark datasets demonstrate that PAGE significantly outperforms state-of-the-art methods, demonstrating its effectiveness for graph anomaly detection.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 959-967
Open AccessPAGE: Progressive Anomaly Generation Network for Semi-supervised Graph Anomaly Detection
Semi-supervised graph anomaly detection confronts the fundamental challenge of identifying anomalous nodes that exhibit deviations from normal graph patterns in node attributes or structure connectivity, using a small set of labeled normal nodes. Existing methods fall short in modeling the spectrum of anomaly severity, as they generate anomalies in a single, undifferentiated step. This oversight restricts the detection of complex anomalies. In this paper, we propose a progressive anomaly generation network (PAGE) to overcome this limitation. PAGE enhances complex anomaly detection through progressive attribute-structure perturbation: It first injects attribute noise into selected normal nodes to generate pseudo-anomalous nodes. Then it applies progressive structure perturbation to create hybrid anomalies that simulate the evolution from mild to complex perturbations. Importantly, the proposed anomaly progressive constraint loss enforces that hybrid anomalies exhibit a higher degree of abnormality than primary anomalies, enhancing the model's anomaly quantification capability. PAGE further integrates deviation constraint loss and classification loss to optimize node representations and improve prediction. Extensive experiments on benchmark datasets demonstrate that PAGE significantly outperforms state-of-the-art methods, demonstrating its effectiveness for graph anomaly detection.
- 11 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107342
Rethinking exploration–exploitation trade-off in reinforcement learning via cognitive consistency
- 11 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107342
Rethinking exploration–exploitation trade-off in reinforcement learning via cognitive consistency