Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation

Abstract

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.

Accepted to WSDM 2022

References in corpus (2)

• Distilling the Knowledge in a Neural Network
• graph2vec: Learning Distributed Representations of Graphs

Cited by in corpus (6)

• Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation
• Soft Prompt Decoding for Multilingual Dense Retrieval
• CVTGAD: Simplified Transformer with Cross-View Attention for Unsupervised Graph-level Anomaly Detection
• Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detection
• Multi-representations Space Separation based Graph-level Anomaly-aware Detection
• Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning