A Universal Adaptive Algorithm for Graph Anomaly Detection

Graph-based anomaly detection aims to identify anomalous vertices in graph-structured data. It relies on the ability of graph neural networks (GNNs) to capture both relational and attribute information within graphs. However, previous GNN-based methods exhibit two critical shortcomings. Firstly, GNN is inherently a low-pass filter that tends to lead similar representations of neighboring vertices, which may result in the loss of critical anomalous information, termed as low-frequency constraints. Secondly, anomalous vertices that deliberately mimic normal vertices in features and structures are hard to detect, especially when the distribution of labels is unbalanced. To address these defects, we propose a Universal Adaptive Algorithm for Graph Anomaly Detection (U-A${}^2$GAD), which employs enhanced high frequency filters to overcome the low-frequency constraints, as well as aggregating both $k$-nearest neighbor ($k$NN) and $k$-farthest neighbor ($k$FN) to resolve the vertices’ camouflage problem. Extensive experiments demonstrated the effectiveness and universality of our proposed U-A${}^2$GAD and its constituent components, achieving improvements of up to 6% and an average increase of 2% on AUC-PR over the state-of-the-art methods. The source codes, and parameter setting details can be found at https://github.com/LIyvqi/U-A2GAD.