Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection

TL;DR

This paper introduces SL-GAD, a self-supervised learning approach combining generative and contrastive modules to improve graph anomaly detection by capturing complex attribute and structure information.

Contribution

The paper proposes a novel self-supervised framework, SL-GAD, that effectively integrates generative and contrastive learning for enhanced graph anomaly detection.

Findings

Outperforms state-of-the-art methods on six benchmark datasets.

Effectively captures anomalies in both attribute and structure spaces.

Demonstrates significant improvements in detection accuracy.

Abstract

Anomaly detection from graph data has drawn much attention due to its practical significance in many critical applications including cybersecurity, finance, and social networks. Existing data mining and machine learning methods are either shallow methods that could not effectively capture the complex interdependency of graph data or graph autoencoder methods that could not fully exploit the contextual information as supervision signals for effective anomaly detection. To overcome these challenges, in this paper, we propose a novel method, Self-Supervised Learning for Graph Anomaly Detection (SL-GAD). Our method constructs different contextual subgraphs (views) based on a target node and employs two modules, generative attribute regression and multi-view contrastive learning for anomaly detection. While the generative attribute regression module allows us to capture the anomalies in the attribute space, the multi-view contrastive learning module can exploit richer structure information from multiple subgraphs, thus abling to capture the anomalies in the structure space, mixing of structure, and attribute information. We conduct extensive experiments on six benchmark datasets and the results demonstrate that our method outperforms state-of-the-art methods by a large margin.