Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks

arXiv:2403.04010v1 Announce Type: new
Abstract: Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks. Despite advancements of methodology based on deep learning in recent years, existing benchmarking approaches exhibit limitations that hinder a comprehensive comparison. In this paper, we revisit datasets and approaches for unsupervised node-level graph anomaly detection tasks from three aspects. Firstly, we introduce outlier injection methods that create more diverse and graph-based anomalies in graph datasets. Secondly, we compare methods employing message …

abstract anomaly anomaly detection arxiv benchmarking comparison cs.lg datasets deep learning detection graph hinder instances limitations methodology networks neural networks node outliers paper role type vital