7 papers
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…
Generalist Graph Anomaly Detection via Prototype-Based Distillation
Yiming Xu, Zihan Chen, Zhen Peng +4
Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector transferable across new graphs,…
Hide and Find: A Distributed Adversarial Attack on Federated Graph Learning
Jinshan Liu, Ken Li, Jiazhe Wei +2
Federated Graph Learning (FedGL) is vulnerable to malicious attacks, yet developing a truly effective and stealthy attack method remains a significant challenge. Existing attack me…
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…
Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection
Yiming Xu, Jiarun Chen, Zhen Peng +5
The natural combination of intricate topological structures and rich textual information in text-attributed graphs (TAGs) opens up a novel perspective for graph anomaly detection (…
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…