Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, Huamin Feng, Yongdong Zhang
Abstract
Graph anomaly detection (GAD) suffers from heterophily — abnormal nodes are sparse so that they are connected to vast normal nodes. The current solutions upon Graph Neural Networks (GNNs) blindly smooth the representation of neiboring nodes, thus undermining the discriminative information of the anomalies. To alleviate the issue, recent studies identify and discard inter-class edges through estimating and comparing the node-level representation similarity. However, the representation of a single node can be misleading when the prediction error is high, thus hindering the performance of the edge indicator.
Topics & Concepts
Computer scienceDiscriminative modelGraphAnomaly detectionNode (physics)Perspective (graphical)Pattern recognition (psychology)Representation (politics)Theoretical computer scienceArtificial intelligenceData miningStructural engineeringEngineeringPoliticsLawPolitical scienceAdvanced Graph Neural NetworksComplex Network Analysis TechniquesAnomaly Detection Techniques and Applications