mlsanityData to 7 Oct 2026

Deep Graph Anomaly Detection: A Survey and New Perspectives

arXiv 2409.09957 ↗First posted 16 Sep 2024cs.LG cs.AIcited by 40

Not on the map. Why?

Abstract (arXiv)

Graph anomaly detection (GAD), which aims to identify unusual graph instances (nodes, edges, subgraphs, or graphs), has attracted increasing attention in recent years due to its significance in a wide range of applications. Deep learning approaches, graph neural networks (GNNs) in particular, have been emerging as a promising paradigm for GAD, owing to its strong capability in capturing complex structure and/or node attributes in graph data. Considering the large number of methods proposed for GNN-based GAD, it is of paramount importance to summarize the methodologies and findings in the existing GAD studies, so that we can pinpoint effective model designs for tackling open GAD problems. To this end, in this work we aim to present a comprehensive review of deep learning approaches for GAD. Existing GAD surveys are focused on task-specific discussions, making it difficult to understand the technical insights of existing methods and their limitations in addressing some unique challenges in GAD. To fill this gap, we first discuss the problem complexities and their resulting challenges in GAD, and then provide a systematic review of current deep GAD methods from three novel perspectives of methodology, including GNN backbone design, proxy task design for GAD, and graph anomaly measures. To deepen the discussions, we further propose a taxonomy of 13 fine-grained method categories under these three perspectives to provide more in-depth insights into the model designs and their capabilities. To facilitate the experiments and validation, we also summarize a collection of widely-used GAD datasets and empirical comparison. We further discuss multiple open problems to inspire more future high-quality research. A continuously updated repository for datasets, links to the codes of algorithms, and empirical comparison is available at https://github.com/mala-lab/Awesome-Deep-Graph-Anomaly-Detection.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 91 of its 176 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

91 of 176 references.

References · 91

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2020Knowledge Distillation: A Surveycited by 1,578
  8. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  9. 2018Deep Graph Infomaxcited by 1,101
  10. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  11. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  12. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
38 more
  1. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  2. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  3. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  4. 2014Graph-based Anomaly Detection and Description: A Surveycited by 182
  5. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  6. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  7. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  8. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 150
  9. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  10. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147
  11. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 121
  12. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  13. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 91
  14. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  15. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  16. 2020AnomalyDAE: Dual autoencoder for anomaly detection on attributed networkscited by 81
  17. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 81
  18. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  19. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  20. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  21. 2021Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detectioncited by 67
  22. 2021Deep Graph-level Anomaly Detection by Glocal Knowledge Distillationcited by 67
  23. 2021Few-shot Network Anomaly Detection via Cross-network Meta-learningcited by 64
  24. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  25. 2019Deep Weakly-supervised Anomaly Detectioncited by 59
  26. 2021Anomaly Detection in Dynamic Graphs via Transformercited by 57
  27. 2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 57
  28. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  29. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 54
  30. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  31. 2021ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networkscited by 51
  32. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 46
  33. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  34. 2023GAD-NR: Graph Anomaly Detection via Neighborhood Reconstructioncited by 44
  35. 2024HiGPT: Heterogeneous Graph Language Modelcited by 44
  36. 2023Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detectioncited by 43
  37. 2020Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Datacited by 42
  38. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41

50 most cited of 91 All 91 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 11; 2026: 27.

40 papers.

Sort:

By area:

  1. 2024Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Promptscited by 24
  2. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 13
  3. 2026From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detectioncited by 8
  4. 2025TAD-Bench: A Comprehensive Benchmark for Embedding-Based Text Anomaly Detectioncited by 6
  5. 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systemscited by 5
  6. 2025Semi-supervised Graph Anomaly Detection via Robust Homophily Learningcited by 4
  7. 2026Towards Anomaly Detection on Relational Datacited by 4
  8. 2025Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detectioncited by 2
  9. 2025Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learningcited by 2
  10. 2024GrokFormer: Graph Fourier Kolmogorov-Arnold Transformerscited by 1
  11. 2025From Pixels to Graphs: Deep Graph-Level Anomaly Detection on Dermoscopic Imagescited by 1
  12. 2025Improving Pattern Recognition of Scheduling Anomalies through Structure-Aware and Semantically-Enhanced Graphscited by 1
28 more
  1. 2026OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detectioncited by 1
  2. 2026NeiGAD: Augmenting Graph Anomaly Detection via Spectral Neighbor Informationcited by 1
  3. 2026Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learningcited by 1
  4. 2025Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detectioncited by 0
  5. 2025Preference Isolation Forest for Structure-based Anomaly Detectioncited by 0
  6. 2025Normality Calibration in Semi-supervised Graph Anomaly Detectioncited by 0
  7. 2025Meta-Learning Based Few-Shot Graph-Level Anomaly Detectioncited by 0
  8. 2026Refining Decision Boundaries In Anomaly Detection Using Similarity Search Within the Feature Spacecited by 0
  9. 2026Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Expertscited by 0
  10. 2026Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervisioncited by 0
  11. 2026TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detectioncited by 0
  12. 2026TAS-GNN: A Status-Aware Signed Graph Neural Network for Anomaly Detection in Bitcoin Trust Systemscited by 0
  13. 2026Financial Anomaly Detection for the Canadian Marketcited by 0
  14. 2026NK-GAD: Neighbor Knowledge-Enhanced Unsupervised Graph Anomaly Detectioncited by 0
  15. 2026GAD in the Wild: Benchmarking Graph Anomaly Detection under Realistic Deployment Challengescited by 0
  16. 2026When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detectioncited by 0
  17. 2026Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detectioncited by 0
  18. 2026TERGAD: Structure-Aware Text-Enhanced Representations for Graph Anomaly Detectioncited by 0
  19. 2026NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversitycited by 0
  20. 2026Generalist Graph Anomaly Detection via Prototype-Based Distillationcited by 0
  21. 2026Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detectioncited by 0
  22. 2026RareSense: Rarity-Aware Similarity Search for Anomaly Retrieval in Transactional Datacited by 0
  23. 2026RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detectioncited by 0
  24. 2026GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detectioncited by 0
  25. 2026Topology-induced Operators Reveal Complementary Graph Representations without Trainingcited by 0
  26. 2026FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detectioncited by 0
  27. 2026DiFA: Dual Evidence Fusion and Aggregation for Token-Level Text Anomaly Detectioncited by 0
  28. 2026The Selection Rule Decides the Winner: A Pre-Registered Audit of Open-Set Graph Anomaly Detectioncited by 0