mlsanityData to 7 Oct 2026

A Comprehensive Survey on Graph Anomaly Detection with Deep Learning

arXiv 2106.07178 ↗First posted 14 Jun 2021cs.LGcited by 230

Not on the map. Why?

Abstract (arXiv)

Anomalies represent rare observations (e.g., data records or events) that deviate significantly from others. Over several decades, research on anomaly mining has received increasing interests due to the implications of these occurrences in a wide range of disciplines. Anomaly detection, which aims to identify rare observations, is among the most vital tasks in the world, and has shown its power in preventing detrimental events, such as financial fraud, network intrusion, and social spam. The detection task is typically solved by identifying outlying data points in the feature space and inherently overlooks the relational information in real-world data. Graphs have been prevalently used to represent the structural information, which raises the graph anomaly detection problem - identifying anomalous graph objects (i.e., nodes, edges and sub-graphs) in a single graph, or anomalous graphs in a database/set of graphs. However, conventional anomaly detection techniques cannot tackle this problem well because of the complexity of graph data. For the advent of deep learning, graph anomaly detection with deep learning has received a growing attention recently. In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection. We compile open-sourced implementations, public datasets, and commonly-used evaluation metrics to provide affluent resources for future studies. More importantly, we highlight twelve extensive future research directions according to our survey results covering unsolved and emerging research problems and real-world applications. With this survey, our goal is to create a "one-stop-shop" that provides a unified understanding of the problem categories and existing approaches, publicly available hands-on resources, and high-impact open challenges for graph anomaly detection using deep learning.

Key facts. Cited by 230 papers in the map (data through 7 Oct 2026). Builds on 81 of its 225 references that are in the map. First posted on arXiv 14 Jun 2021.

Builds on

81 of 225 references.

References · 81

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  6. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  8. 2016Variational Graph Auto-Encoderscited by 1,373
  9. 2015LINE: Large-scale Information Network Embeddingcited by 582
  10. 2017Representation Learning on Graphs: Methods and Applicationscited by 456
  11. 2015Unsupervised Learning of Video Representations using LSTMscited by 434
  12. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
38 more
  1. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  2. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  3. 2018Adversarial Attack on Graph Structured Datacited by 300
  4. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  5. 2019Representation Learning for Dynamic Graphs: A Surveycited by 260
  6. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  7. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  8. 2014Graph-based Anomaly Detection and Description: A Surveycited by 182
  9. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  10. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  11. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  12. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 150
  13. 2017A Survey on Network Embeddingcited by 142
  14. 2018Multi-task Deep Reinforcement Learning with PopArtcited by 138
  15. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  16. 2020GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Mediacited by 108
  17. 2020FANG: Leveraging Social Context for Fake News Detection Using Graph Representationcited by 98
  18. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 95
  19. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 85
  20. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  21. 2020AnomalyDAE: Dual autoencoder for anomaly detection on attributed networkscited by 81
  22. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 81
  23. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  24. 2021User Preference-aware Fake News Detectioncited by 76
  25. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  26. 2020Subgraph Neural Networkscited by 73
  27. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  28. 2021Few-shot Network Anomaly Detection via Cross-network Meta-learningcited by 64
  29. 2021A Comprehensive Survey on Community Detection with Deep Learningcited by 63
  30. 2020Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphscited by 55
  31. 2020Graph Geometry Interaction Learningcited by 55
  32. 2018A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Taskscited by 54
  33. 2020GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detectioncited by 53
  34. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  35. 2020Heterogeneous Hypergraph Embedding for Graph Classificationcited by 52
  36. 2020Deep Learning for Community Detection: Progress, Challenges and Opportunitiescited by 42
  37. 2016Fast Memory-efficient Anomaly Detection in Streaming Heterogeneous Graphscited by 37
  38. 2019SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networkscited by 37

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 53; 2023: 54; 2024: 48; 2025: 38; 2026: 31.

230 papers.

Sort:

By area:

  1. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  2. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  3. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  4. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  5. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 79
  6. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  7. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
  8. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  9. 2023Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunitiescited by 60
  10. 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
  11. 2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 57
  12. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 54
38 more
  1. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  2. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 46
  3. 2023GAD-NR: Graph Anomaly Detection via Neighborhood Reconstructioncited by 44
  4. 2023Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detectioncited by 43
  5. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  6. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  7. 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modelingcited by 35
  8. 2024Graph Transformers: A Surveycited by 32
  9. 2022PyGOD: A Python Library for Graph Outlier Detectioncited by 31
  10. 2022Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignmentcited by 31
  11. 2024Alleviating Structural Distribution Shift in Graph Anomaly Detectioncited by 31
  12. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  13. 2023SAD: Semi-Supervised Anomaly Detection on Dynamic Graphscited by 27
  14. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  15. 2022A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resourcecited by 26
  16. 2024Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Promptscited by 24
  17. 2024Graph Neural Networks for Financial Fraud Detection: A Reviewcited by 24
  18. 2025A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detectioncited by 24
  19. 2022Graph Anomaly Detection with Graph Neural Networks: Current Status and Challengescited by 23
  20. 2023ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detectioncited by 23
  21. 2023Label Information Enhanced Fraud Detection against Low Homophily in Graphscited by 22
  22. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  23. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  24. 2025Large Language Models are Good Relational Learnerscited by 22
  25. 2022A Survey of Graph-based Deep Learning for Anomaly Detection in Distributed Systemscited by 20
  26. 2022DAGAD: Data Augmentation for Graph Anomaly Detectioncited by 20
  27. 2024Continual Learning on Graphs: Challenges, Solutions, and Opportunitiescited by 20
  28. 2022Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspectivecited by 19
  29. 2023Financial Fraud Detection: A Comparative Study of Quantum Machine Learning Modelscited by 19
  30. 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
  31. 2024Anomaly Detection in Dynamic Graphs: A Comprehensive Surveycited by 18
  32. 2022Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Methodcited by 15
  33. 2022Graph Learning for Anomaly Analytics: Algorithms, Applications, and Challengescited by 15
  34. 2023Dynamic Graph Representation Learning with Neural Networks: A Surveycited by 15
  35. 2023Towards Semi-supervised Universal Graph Classificationcited by 15
  36. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  37. 2025Deep Learning Advancements in Anomaly Detection: A Comprehensive Surveycited by 15
  38. 2021An Efficient Federated Distillation Learning System for Multi-task Time Series Classificationcited by 14

50 most cited of 230 All 230 (JSON)