# Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation

arXiv: https://arxiv.org/abs/2306.10534 · HTML: https://mlsanity.com/paper/2306.10534/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 79 references that are in the map.
- First posted on arXiv 18 Jun 2023.

## Builds on (most cited first, 30 of 41)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [A Comprehensive Survey on Graph Anomaly Detection with Deep Learning](https://mlsanity.com/paper/2106.07178/) (2021)
- [Rethinking Graph Neural Networks for Anomaly Detection](https://mlsanity.com/paper/2205.15508/) (2022)
- [Graph-based Anomaly Detection and Description: A Survey](https://mlsanity.com/paper/1404.4679/) (2014)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [A Semi-supervised Graph Attentive Network for Financial Fraud Detection](https://mlsanity.com/paper/2003.01171/) (2020)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Data Augmentation for Deep Graph Learning: A Survey](https://mlsanity.com/paper/2202.08235/) (2022)
- [Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains](https://mlsanity.com/paper/2007.02035/) (2020)
- [Inferring Networks of Substitutable and Complementary Products](https://mlsanity.com/paper/1506.08839/) (2015)
- [BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs](https://mlsanity.com/paper/2206.10071/) (2022)
- [Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks](https://mlsanity.com/paper/1805.07925/) (2018)
- [Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection](https://mlsanity.com/paper/2108.09896/) (2021)

## Built on by (most cited first, 11 of 11)

- [Deep Graph Anomaly Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2409.09957/) (2024)
- [A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models](https://mlsanity.com/paper/2509.06609/) (2025)
- [Open-Set Graph Anomaly Detection via Normal Structure Regularisation](https://mlsanity.com/paper/2311.06835/) (2023)
- [IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2502.06280/) (2025)
- [Semi-supervised Graph Anomaly Detection via Robust Homophily Learning](https://mlsanity.com/paper/2506.15448/) (2025)
- [UMGAD: Unsupervised Multiplex Graph Anomaly Detection](https://mlsanity.com/paper/2411.12556/) (2024)
- [Balanced Edge Pruning for Graph Anomaly Detection with Noisy Labels](https://mlsanity.com/paper/2407.05934/) (2024)
- [Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning](https://mlsanity.com/paper/2503.12037/) (2025)
- [Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection](https://mlsanity.com/paper/2504.14250/) (2025)
- [Multi-Modal Anomaly Detection: A Survey](https://mlsanity.com/paper/2608.24937/) (2026)
- [CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection](https://mlsanity.com/paper/2609.01425/) (2026)

## Abstract (arXiv)

Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage the available labels as prior knowledge, have achieved superior performances than unsupervised methods. In practice, people usually need to identify anomalies on new (sub)graphs to secure their business, but they may lack labels to train an effective detection model. One natural idea is to directly adopt a trained GAD model to the new (sub)graph for testing. However, we find that existing semi-supervised GAD methods suffer from poor generalization issue, i.e., well-trained models could not perform well on an unseen area (i.e., not accessible in training) of the same graph. It may cause great troubles. In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers. Nevertheless, it is a challenging task since only limited labels are available, and the normal background may differ between training and testing data. Accordingly, we propose a data augmentation method named textitAugAN (ulineAugmentation for ulineAnomaly and ulineNormal distributions) to enrich training data and boost the generalizability of GAD models. Experiments verify the effectiveness of our method in improving model generalizability.