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

Researchers introduce ANOMIX, a new framework that improves graph neural network anomaly detection by generating hard negative samples through mixup techniques. The method addresses the limitation of existing GNN-based detection systems that struggle with subtle boundary anomalies by creating more robust decision boundaries.

• →Current GNN-based anomaly detection methods excel at obvious outliers but fail with subtle boundary anomalies
• →ANOMIX synthesizes hard negative samples by interpolating normal and abnormal subgraph representations
• →The framework populates decision boundaries with challenging samples to improve detection accuracy
• →Experimental results show clear separation of boundary anomalies where existing methods fail
• →The approach enhances GNN reasoning capacity for more reliable graph anomaly detection