AI RESEARCH
NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity
arXiv CS.LG
•
ArXi:2605.20879v1 Announce Type: new Graph Anomaly Detection (GAD) is increasingly shifting to Generalist GAD (GGAD) for cross-domain "one-for-all" detection, but existing GGAD methods predominantly rely on the neighbor consistency principle, falling into the \textbf{Node-to-Neighbor Consistency Paradigm} for anomaly quantification. These methods suffer from complex