Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
This addresses the problem of identifying abnormal graphs in diverse domains, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the challenge of detecting both locally- and globally-anomalous graphs in graph-level anomaly detection by introducing a deep approach that learns normal patterns through joint random distillation of graph and node representations, achieving significant outperformance over seven state-of-the-art models on 16 real-world datasets.
Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs, i.e., graphs that are abnormal in their fine-grained (node-level) or holistic (graph-level) properties, respectively. To tackle this challenge we introduce a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations. The random distillation is achieved by training one GNN to predict another GNN with randomly initialized network weights. Extensive experiments on 16 real-world graph datasets from diverse domains show that our model significantly outperforms seven state-of-the-art models. Code and datasets are available at https://git.io/GLocalKD.