Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View

Authors

  • Jingcan Duan National University of Defense Technology
  • Siwei Wang National University of Defense Technology
  • Pei Zhang National University of Defense Technology
  • En Zhu National University of Defense Technology
  • Jingtao Hu National University of Defense Technology
  • Hu Jin National University of Defense Technology
  • Yue Liu National University of Defense Technology
  • Zhibin Dong National University of Defense Technology

DOI:

https://doi.org/10.1609/aaai.v37i6.25907

Keywords:

ML: Multi-Instance/Multi-View Learning, ML: Graph-based Machine Learning

Abstract

Graph anomaly detection (GAD) is a vital task in graph-based machine learning and has been widely applied in many real-world applications. The primary goal of GAD is to capture anomalous nodes from graph datasets, which evidently deviate from the majority of nodes. Recent methods have paid attention to various scales of contrastive strategies for GAD, i.e., node-subgraph and node-node contrasts. However, they neglect the subgraph-subgraph comparison information which the normal and abnormal subgraph pairs behave differently in terms of embeddings and structures in GAD, resulting in sub-optimal task performance. In this paper, we fulfill the above idea in the proposed multi-view multi-scale contrastive learning framework with subgraph-subgraph contrast for the first practice. To be specific, we regard the original input graph as the first view and generate the second view by graph augmentation with edge modifications. With the guidance of maximizing the similarity of the subgraph pairs, the proposed subgraph-subgraph contrast contributes to more robust subgraph embeddings despite of the structure variation. Moreover, the introduced subgraph-subgraph contrast cooperates well with the widely-adopted node-subgraph and node-node contrastive counterparts for mutual GAD performance promotions. Besides, we also conduct sufficient experiments to investigate the impact of different graph augmentation approaches on detection performance. The comprehensive experimental results well demonstrate the superiority of our method compared with the state-of-the-art approaches and the effectiveness of the multi-view subgraph pair contrastive strategy for the GAD task. The source code is released at https://github.com/FelixDJC/GRADATE.

Downloads

Published

2023-06-26

How to Cite

Duan, J., Wang, S., Zhang, P., Zhu, E., Hu, J., Jin, H., Liu, Y., & Dong, Z. (2023). Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View. Proceedings of the AAAI Conference on Artificial Intelligence, 37(6), 7459-7467. https://doi.org/10.1609/aaai.v37i6.25907

Issue

Section

AAAI Technical Track on Machine Learning I