Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks
This work addresses benchmarking issues for researchers in graph anomaly detection, but it is incremental as it revisits and refines existing approaches rather than proposing a new paradigm.
The paper tackled limitations in benchmarking for unsupervised node-level graph anomaly detection by introducing outlier injection methods for diverse anomalies, comparing message passing methods (which unexpectedly reduced performance), and exploring hyperbolic neural networks with specific designs that improved results.
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 passing against those without, uncovering the unexpected decline in performance associated with message passing. Thirdly, we explore the use of hyperbolic neural networks, specifying crucial architecture and loss design that contribute to enhanced performance. Through rigorous experiments and evaluations, our study sheds light on general strategies for improving node-level graph anomaly detection methods.