mlsanityData to 14 Oct 2026

GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection

arXiv 2306.12251 ↗First posted 21 Jun 2023cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

With a long history of traditional Graph Anomaly Detection (GAD) algorithms and recently popular Graph Neural Networks (GNNs), it is still not clear (1) how they perform under a standard comprehensive setting, (2) whether GNNs can outperform traditional algorithms such as tree ensembles, and (3) how about their efficiency on large-scale graphs. In response, we introduce GADBench -- a benchmark tool dedicated to supervised anomalous node detection in static graphs. GADBench facilitates a detailed comparison across 29 distinct models on ten real-world GAD datasets, encompassing thousands to millions (~6M) nodes. Our main finding is that tree ensembles with simple neighborhood aggregation can outperform the latest GNNs tailored for the GAD task. We shed light on the current progress of GAD, setting a robust groundwork for subsequent investigations in this domain. GADBench is open-sourced at https://github.com/squareRoot3/GADBench.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). Builds on 47 of its 105 references that are in the map. First posted on arXiv 21 Jun 2023.

Builds on

47 of 105 references.

References · 47

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  9. 2019Simplifying Graph Convolutional Networkscited by 1,477
  10. 2020Heterogeneous Graph Transformercited by 582
  11. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  12. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
35 more
  1. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
  2. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  3. 2016Generalized Random Forestscited by 312
  4. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
  5. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 250
  6. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  7. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  8. 2019PyOD: A Python Toolbox for Scalable Outlier Detectioncited by 222
  9. 2021Accounting for Variance in Machine Learning Benchmarkscited by 201
  10. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  11. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 187
  12. 2014Graph-based Anomaly Detection and Description: A Surveycited by 183
  13. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 164
  14. 2020Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networkscited by 153
  15. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 151
  16. 2013From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviewscited by 108
  17. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 93
  18. 2022Graph Attention Multi-Layer Perceptroncited by 83
  19. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 82
  20. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  21. 2018GeniePath: Graph Neural Networks with Adaptive Receptive Pathscited by 66
  22. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  23. 2019Spam Review Detection with Graph Convolutional Networkscited by 57
  24. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 55
  25. 2020Rethinking Assumptions in Deep Anomaly Detectioncited by 45
  26. 2021Boost then Convolve: Gradient Boosting Meets Graph Neural Networkscited by 44
  27. 2019XGBOD: Improving Supervised Outlier Detection with Unsupervised Representation Learningcited by 42
  28. 2023Weakly Supervised Anomaly Detection: A Surveycited by 22
  29. 2022DAGAD: Data Augmentation for Graph Anomaly Detectioncited by 20
  30. 2020Robust Spammer Detection by Nash Reinforcement Learningcited by 17
  31. 2019Imbalance-XGBoost: Leveraging Weighted and Focal Losses for Binary Label-Imbalanced Classification with XGBoostcited by 15
  32. 2021Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node featurescited by 9
  33. 2022Mul-GAD: a semi-supervised graph anomaly detection framework via aggregating multi-view informationcited by 7
  34. 2023Revisiting Graph Contrastive Learning for Anomaly Detectioncited by 4
  35. 2023Neighborhood Averaging for Improving Outlier Detectorscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 23; 2025: 15; 2026: 16.

58 papers.

Sort:

By area:

  1. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 86
  2. 2024ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphscited by 85
  3. 2024GraphArena: Evaluating and Exploring Large Language Models on Graph Computationcited by 49
  4. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 48
  5. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  6. 2024Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Promptscited by 28
  7. 2023SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biasescited by 27
  8. 2025AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detectioncited by 23
  9. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  10. 2024Anomaly Detection in Dynamic Graphs: A Comprehensive Surveycited by 19
  11. 2024Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmarkcited by 18
  12. 2024UniGAD: Unifying Multi-level Graph Anomaly Detectioncited by 14
38 more
  1. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 14
  2. 2023Open-Set Graph Anomaly Detection via Normal Structure Regularisationcited by 11
  3. 2024SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detectioncited by 11
  4. 2024Weakly Supervised Anomaly Detection via Knowledge-Data Alignmentcited by 10
  5. 2025FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detectioncited by 10
  6. 2025Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspectivecited by 8
  7. 2026From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detectioncited by 8
  8. 2024From Graphs to Qubits: A Critical Review of Quantum Graph Neural Networkscited by 6
  9. 2024GuARD: Effective Anomaly Detection through a Text-Rich and Graph-Informed Language Modelcited by 6
  10. 2024Deep Reinforcement Learning for Modelling Protein Complexescited by 5
  11. 2025Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learningcited by 5
  12. 2025Semi-supervised Graph Anomaly Detection via Robust Homophily Learningcited by 4
  13. 2023Coupled-Space Attacks against Random-Walk-based Anomaly Detectioncited by 2
  14. 2024Relational Graph Convolutional Networks Do Not Learn Sound Rulescited by 2
  15. 2024UMGAD: Unsupervised Multiplex Graph Anomaly Detectioncited by 2
  16. 2026Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detectioncited by 2
  17. 2023Data Augmentation for Supervised Graph Outlier Detection via Latent Diffusion Modelscited by 1
  18. 2024Qsco: A Quantum Scoring Module for Open-set Supervised Anomaly Detectioncited by 1
  19. 2024Addressing Graph Heterogeneity and Heterophily from A Spectral Perspectivecited by 1
  20. 2024Graph Pre-Training Models Are Strong Anomaly Detectorscited by 1
  21. 2024TGTOD: A Global Temporal Graph Transformer for Outlier Detection at Scalecited by 1
  22. 2026AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detectioncited by 1
  23. 2026Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detectioncited by 1
  24. 2024Balanced Edge Pruning for Graph Anomaly Detection with Noisy Labelscited by 0
  25. 2024Deep Generative Models for Subgraph Predictioncited by 0
  26. 2025A Novel Spatiotemporal Correlation Anomaly Detection Method Based on Time-Frequency-Domain Feature Fusion and a Dynamic Graph Neural Network in Wireless Sensor Networkcited by 0
  27. 2025CRC-SGAD: Conformal Risk Control for Supervised Graph Anomaly Detectioncited by 0
  28. 2025Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detectioncited by 0
  29. 2025Enhancing Spectral Graph Neural Networks with LLM-Predicted Homophilycited by 0
  30. 2025Robust Anomaly Detection with Graph Neural Networks using Controllabilitycited by 0
  31. 2025CRoC: Context Refactoring Contrast for Graph Anomaly Detection with Limited Supervisioncited by 0
  32. 2025DyC-STG: Dynamic Causal Spatio-Temporal Graph Network for Real-time Data Credibility Analysis in IoTcited by 0
  33. 2025Generative Dynamic Graph Representation Learning for Conspiracy Spoofing Detectioncited by 0
  34. 2025Combining Euclidean and Hyperbolic Representations for Node-level Anomaly Detectioncited by 0
  35. 2026Bridging Cognitive Neuroscience and Graph Intelligence: Hippocampus-Inspired Multi-View Hypergraph Learning for Web Finance Fraudcited by 0
  36. 2026Mitigating Homophily Disparity in Graph Anomaly Detection: A Scalable and Adaptive Approachcited by 0
  37. 2026TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detectioncited by 0
  38. 2026Graph-Based Fraud Detection with Dual-Path Graph Filteringcited by 0

50 most cited of 58 All 58 (JSON)