Multi-representations Space Separation based Graph-level Anomaly-aware Detection

TL;DR

This paper introduces a novel graph-level anomaly detection framework that learns separate normal and abnormal graph representation spaces and weights their importance, improving detection accuracy especially for subtle anomalies.

Contribution

It proposes a multi-representations space separation method with an anomaly-aware module to weight node and graph-level anomalies differently, enhancing detection of subtle abnormal graphs.

Findings

Effective detection on ten public datasets

Outperforms baseline methods in accuracy

Separates normal and abnormal graph spaces successfully

Abstract

Graph structure patterns are widely used to model different area data recently. How to detect anomalous graph information on these graph data has become a popular research problem. The objective of this research is centered on the particular issue that how to detect abnormal graphs within a graph set. The previous works have observed that abnormal graphs mainly show node-level and graph-level anomalies, but these methods equally treat two anomaly forms above in the evaluation of abnormal graphs, which is contrary to the fact that different types of abnormal graph data have different degrees in terms of node-level and graph-level anomalies. Furthermore, abnormal graphs that have subtle differences from normal graphs are easily escaped detection by the existing methods. Thus, we propose a multi-representations space separation based graph-level anomaly-aware detection framework in this paper. To consider the different importance of node-level and graph-level anomalies, we design an anomaly-aware module to learn the specific weight between them in the abnormal graph evaluation process. In addition, we learn strictly separate normal and abnormal graph representation spaces by four types of weighted graph representations against each other including anchor normal graphs, anchor abnormal graphs, training normal graphs, and training abnormal graphs. Based on the distance error between the graph representations of the test graph and both normal and abnormal graph representation spaces, we can accurately determine whether the test graph is anomalous. Our approach has been extensively evaluated against baseline methods using ten public graph datasets, and the results demonstrate its effectiveness.