Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
The proposed indicator can effectively reduce the heterophily degree of the graph, thus boosting the overall GAD performance and showing that prediction errors are less likely to affect the identification process.
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.