Toward Reasoning on the Boundary: A Mixup-based Approach for Graph Anomaly Detection

TL;DR

This paper introduces ANOMIX, a novel graph mixup framework that synthesizes hard negatives to improve the detection of boundary anomalies in graphs, addressing the limitations of existing GNN methods.

Contribution

ANOMIX is the first approach to generate informative hard negatives via mixup for boundary anomaly detection in graphs, enhancing reasoning capabilities of GNNs.

Findings

ANOMIX effectively separates boundary anomalies from normal nodes.

The method improves detection performance on challenging boundary cases.

Experimental results outperform state-of-the-art baselines.

Abstract

While GNN-based detection methods excel at identifying overt outliers, they often struggle with boundary anomalies -- subtly camouflaged nodes that are difficult to distinguish from normal instances. This limitation highlights a fundamental gap in the reasoning capabilities of existing methods. We attribute this issue to the reliance of standard Graph Contrastive Learning (GCL) on easy negatives, which fosters the learning of simplistic decision boundaries. To address this issue, we propose ANOMIX, a framework that synthesizes informative hard negatives by linearly interpolating representations of normal and abnormal subgraphs. This graph mixup strategy intentionally populates the decision boundary with hard-to-detect samples. Through targeted experimental analysis, we demonstrate that ANOMIX successfully separates these boundary anomalies where state-of-the-art baselines fail, as shown by a clear distinction in the score distributions for these challenging cases. These findings suggest that synthesizing hard negatives via mixup is a potent strategy for refining GNN representation space, which in turn enhances its reasoning capacity for more robust and reliable graph anomaly detection. Code is available at https://github.com/missinghwan/ANOMIX.