ANOMIX: A Simple yet Effective Hard Negative Generation via Mixing for Graph Anomaly Detection
This addresses the challenge of imbalanced data and limited anomalies in graph anomaly detection, offering an incremental improvement in efficiency and accuracy for this domain-specific task.
The paper tackles the problem of graph anomaly detection by proposing ANOMIX, a framework that uses a novel graph mixing approach to generate hard negatives for graph contrastive learning, resulting in up to 5.49% higher AUC and reducing the number of samples by nearly 80%.
Graph contrastive learning (GCL) generally requires a large number of samples. The one of the effective ways to reduce the number of samples is using hard negatives (e.g., Mixup). Designing mixing-based approach for GAD can be difficult due to imbalanced data or limited number of anomalies. We propose ANOMIX, a framework that consists of a novel graph mixing approach, ANOMIX-M, and multi-level contrasts for GAD. ANOMIX-M can effectively mix abnormality and normality from input graph to generate hard negatives, which are important for efficient GCL. ANOMIX is (a) A first mixing approach: firstly attempting graph mixing to generate hard negatives for GAD task and node- and subgraph-level contrasts to distinguish underlying anomalies. (b) Accurate: winning the highest AUC, up to 5.49% higher and 1.76% faster. (c) Effective: reducing the number of samples nearly 80% in GCL. Code is available at https://github.com/missinghwan/ANOMIX.