3 papers
cs.LG2026
Learning Dynamic Graph Representations through Timespan View Contrasts
Yiming Xu, Zhen Peng, Bin Shi +2
The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node features and topological prop…
cs.LG2025
Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learning
Yiming Xu, Xu Hua, Zhen Peng +5
The widespread application of graph data in various high-risk scenarios has increased attention to graph anomaly detection (GAD). Faced with real-world graphs that often carry node…
cs.LG2025
Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective
Yiming Xu, Zhen Peng, Bin Shi +4
The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-base…