GLADformer: A Mixed Perspective for Graph-Level Anomaly Detection

Abstract

Graph-Level Anomaly Detection (GLAD) aims to distinguish anomalous graphs within a graph data set. However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs. Moreover, most these methods are based on spatial domain and lack exploration of spectral characteristics. In this paper, we propose a multi-perspective hybrid graph-level anomaly detector named GLADformer, consisting of two key modules. Specifically, we first design a Graph Transformer module with global spectrum enhancement, which ensures balanced and resilient parameter distributions by fusing global features and spectral distribution characteristics. Furthermore, to explore local anomalous attributes, we customize a band-pass spectral GNN message passing module that enhances the model’s generalization capability. Through comprehensive experiments on ten real-world datasets from multiple domains, we validate the effectiveness and robustness of GLADformer. This demonstrates that GLADformer outperforms current state-of-the-art graph-level anomaly detection methods, particularly in effectively capturing global anomaly representations and spectral characteristics.