重新审视用于异常检测的图对比学习
Revisiting Graph Contrastive Learning for Anomaly Detection
AI总结：
该研究重新审视图对比异常检测机制，纠正了多尺度模块贡献的认知误区，提出统一现有方法的MAG框架，其两种变体在低计算成本下实现了更优的异常检测性能。
摘要：
近年来，将图神经网络（GNNs）与对比学习结合用于异常检测受到越来越多的关注。现有的图对比异常检测（GCAD）方法主要通过图增强和多尺度对比模块来提升检测能力，但这些模块的底层作用机制尚未得到充分探究。我们深入研究了多尺度与图增强机制，观察到多尺度对比模块并不会增强表征能力，而多GNN模块才是隐性的贡献因素。以往研究往往将多GNN带来的增益归因于多尺度模块。本文深入剖析了这一认知误区，提出了多GNN与增强图对比框架MAG，该框架从对比自监督的视角统一了现有的GCAD方法。我们从MAG框架中提取出两种变体：L-MAG和M-MAG。L-MAG是MAG的轻量实例，在Cora和Pubmed数据集上以较低的计算成本超越了当前最优方法。配备多GNN模块的变体M-MAG则进一步提升了检测性能。本研究揭示了现有GCAD方法的不足，证明了多GNN与图增强模块的潜力。我们的代码可在https://github.com/liuyishoua/MAG-Framework 获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
