Revisiting Graph Contrastive Learning for Anomaly Detection
This addresses a misconception in graph-based anomaly detection research, offering a more efficient and effective approach for detecting anomalies in graph data.
The paper tackles the problem of understanding how graph contrastive learning modules work for anomaly detection, finding that multi-GNN modules are key contributors rather than multi-scale contrast modules, and proposes a framework (MAG) with variants that outperform state-of-the-art methods on Cora and Pubmed datasets with low computational cost.
Combining Graph neural networks (GNNs) with contrastive learning for anomaly detection has drawn rising attention recently. Existing graph contrastive anomaly detection (GCAD) methods have primarily focused on improving detection capability through graph augmentation and multi-scale contrast modules. However, the underlying mechanisms of how these modules work have not been fully explored. We dive into the multi-scale and graph augmentation mechanism and observed that multi-scale contrast modules do not enhance the expression, while the multi-GNN modules are the hidden contributors. Previous studies have tended to attribute the benefits brought by multi-GNN to the multi-scale modules. In the paper, we delve into the misconception and propose Multi-GNN and Augmented Graph contrastive framework MAG, which unified the existing GCAD methods in the contrastive self-supervised perspective. We extracted two variants from the MAG framework, L-MAG and M-MAG. The L-MAG is the lightweight instance of the MAG, which outperform the state-of-the-art on Cora and Pubmed with the low computational cost. The variant M-MAG equipped with multi-GNN modules further improve the detection performance. Our study sheds light on the drawback of the existing GCAD methods and demonstrates the potential of multi-GNN and graph augmentation modules. Our code is available at https://github.com/liuyishoua/MAG-Framework.