DAGAD: Data Augmentation for Graph Anomaly Detection

TL;DR

This paper introduces DAGAD, a novel data augmentation framework for graph anomaly detection that addresses class imbalance and scarce anomalous samples, significantly improving detection performance.

Contribution

The paper proposes a new graph anomaly detection method using data augmentation and tailored learning modules to enhance detection of rare anomalies.

Findings

DAGAD outperforms ten baseline detectors on three datasets.

The data augmentation module effectively increases anomalous sample diversity.

Ablation studies confirm the importance of each module.

Abstract

Graph anomaly detection in this paper aims to distinguish abnormal nodes that behave differently from the benign ones accounting for the majority of graph-structured instances. Receiving increasing attention from both academia and industry, yet existing research on this task still suffers from two critical issues when learning informative anomalous behavior from graph data. For one thing, anomalies are usually hard to capture because of their subtle abnormal behavior and the shortage of background knowledge about them, which causes severe anomalous sample scarcity. Meanwhile, the overwhelming majority of objects in real-world graphs are normal, bringing the class imbalance problem as well. To bridge the gaps, this paper devises a novel Data Augmentation-based Graph Anomaly Detection (DAGAD) framework for attributed graphs, equipped with three specially designed modules: 1) an information fusion module employing graph neural network encoders to learn representations, 2) a graph data augmentation module that fertilizes the training set with generated samples, and 3) an imbalance-tailored learning module to discriminate the distributions of the minority (anomalous) and majority (normal) classes. A series of experiments on three datasets prove that DAGAD outperforms ten state-of-the-art baseline detectors concerning various mostly-used metrics, together with an extensive ablation study validating the strength of our proposed modules.