AI RESEARCH
NK-GAD: Neighbor Knowledge-Enhanced Unsupervised Graph Anomaly Detection
arXiv CS.LG
•
ArXi:2604.15668v1 Announce Type: new Graph anomaly detection aims to identify irregular patterns in graph-structured data. Most unsupervised GNN-based methods rely on the homophily assumption that connected nodes share similar attributes. However, real-world graphs often exhibit attribute-level heterophily, where connected nodes have dissimilar attributes.