FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervision
This addresses the challenge of high labeling costs and dataset imbalance in graph-level anomaly detection for domains like drug discovery, representing an incremental advancement over existing methods.
The paper tackled the problem of graph-level anomaly detection under limited supervision and data imbalance by proposing FracAug, a plug-in augmentation framework that generates semantic-preserving graph variants and uses pseudo-labeling, resulting in consistent performance gains across 14 GNNs on 12 datasets, with improvements of up to 5.72% in AUROC, 7.23% in AUPRC, and 4.18% in F1-score.
Graph-level anomaly detection (GAD) is critical in diverse domains such as drug discovery, yet high labeling costs and dataset imbalance hamper the performance of Graph Neural Networks (GNNs). To address these issues, we propose FracAug, an innovative plug-in augmentation framework that enhances GNNs by generating semantically consistent graph variants and pseudo-labeling with mutual verification. Unlike previous heuristic methods, FracAug learns semantics within given graphs and synthesizes fractional variants, guided by a novel weighted distance-aware margin loss. This captures multi-scale topology to generate diverse, semantic-preserving graphs unaffected by data imbalance. Then, FracAug utilizes predictions from both original and augmented graphs to pseudo-label unlabeled data, iteratively expanding the training set. As a model-agnostic module compatible with various GNNs, FracAug demonstrates remarkable universality and efficacy: experiments across 14 GNNs on 12 real-world datasets show consistent gains, boosting average AUROC, AUPRC, and F1-score by up to 5.72%, 7.23%, and 4.18%, respectively.