Graph Anomaly Detection
UniGAD: Unifying Multi-level Graph Anomaly Detection
·2482 words·12 mins·
loading
·
loading
Machine Learning
Graph Anomaly Detection
🏢 Tsinghua University
UniGAD unifies multi-level graph anomaly detection, improving accuracy and zero-shot transferability by jointly modeling node, edge, and graph anomalies via a novel subgraph sampler and GraphStitch Ne…