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

arXiv: https://arxiv.org/abs/2410.20310 · HTML: https://mlsanity.com/paper/2410.20310/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 27 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [G-Mixup: Graph Data Augmentation for Graph Classification](https://mlsanity.com/paper/2202.07179/) (2022)
- [Few-shot Network Anomaly Detection via Cross-network Meta-learning](https://mlsanity.com/paper/2102.11165/) (2021)
- [Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View](https://mlsanity.com/paper/2212.00535/) (2022)
- [Semi-supervised Anomaly Detection on Attributed Graphs](https://mlsanity.com/paper/2002.12011/) (2020)

## Abstract (arXiv)

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.