Raising the Bar in Graph-level Anomaly Detection
This work addresses the challenge of detecting abnormal graphs in applications like financial fraud and social networks, representing an incremental advance in a domain-specific area.
The paper tackles the problem of graph-level anomaly detection, where existing deep learning methods underperform compared to those for visual data, and presents a new approach that achieves an average 11.8% AUC improvement over the best existing method.
Graph-level anomaly detection has become a critical topic in diverse areas, such as financial fraud detection and detecting anomalous activities in social networks. While most research has focused on anomaly detection for visual data such as images, where high detection accuracies have been obtained, existing deep learning approaches for graphs currently show considerably worse performance. This paper raises the bar on graph-level anomaly detection, i.e., the task of detecting abnormal graphs in a set of graphs. By drawing on ideas from self-supervised learning and transformation learning, we present a new deep learning approach that significantly improves existing deep one-class approaches by fixing some of their known problems, including hypersphere collapse and performance flip. Experiments on nine real-world data sets involving nine techniques reveal that our method achieves an average performance improvement of 11.8% AUC compared to the best existing approach.