Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2022

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.

Keywords

Graph-level anomaly detection, Graph neural networks, Knowledge distillation, Deep learning

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 15th ACM International Conference on Web Search and Data Mining, Virtual Conference, 2022 February 21-25

First Page

704

Last Page

714

ISBN

9781450391320

Identifier

10.1145/3488560.3498473

Publisher

ACM

City or Country

Virtual Conference

Share

COinS