mlsanityData to 7 Oct 2026

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

arXiv 2406.15523 ↗First posted 21 Jun 2024cs.LG stat.MLcited by 18

Not on the map. Why?

Abstract (arXiv)

To build safe and reliable graph machine learning systems, unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection (GLOD) have received significant attention in recent years. Though those two lines of research indeed share the same objective, they have been studied independently in the community due to distinct evaluation setups, creating a gap that hinders the application and evaluation of methods from one to the other. To bridge the gap, in this work, we present a underlineUnified underlineBenchmark for unsupervised underlineGraph-level underlineOOD and anomaunderlineLy underlineDetection (ourmethod), a comprehensive evaluation framework that unifies GLAD and GLOD under the concept of generalized graph-level OOD detection. Our benchmark encompasses 35 datasets spanning four practical anomaly and OOD detection scenarios, facilitating the comparison of 18 representative GLAD/GLOD methods. We conduct multi-dimensional analyses to explore the effectiveness, OOD sensitivity spectrum, robustness, and efficiency of existing methods, shedding light on their strengths and limitations. Furthermore, we provide an open-source codebase (https://github.com/UB-GOLD/UB-GOLD) of ourmethod to foster reproducible research and outline potential directions for future investigations based on our insights.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 36 of its 71 references that are in the map. First posted on arXiv 21 Jun 2024.

Builds on

36 of 71 references.

References · 36

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  5. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  6. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  8. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  9. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  10. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  11. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  12. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
24 more
  1. 2021Graph Learning: A Surveycited by 140
  2. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  3. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  4. 2016Low Data Drug Discovery with One-shot Learningcited by 91
  5. 2014Propagation Kernelscited by 88
  6. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  7. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  8. 2021Deep Graph-level Anomaly Detection by Glocal Knowledge Distillationcited by 67
  9. 2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 57
  10. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  11. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  12. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  13. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 46
  14. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  15. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  16. 2023PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detectioncited by 25
  17. 2024Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Modelscited by 21
  18. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  19. 2024GOODAT: Towards Test-time Graph Out-of-Distribution Detectioncited by 17
  20. 2023Unraveling Privacy Risks of Individual Fairness in Graph Neural Networkscited by 16
  21. 2024CVTGAD: Simplified Transformer with Cross-View Attention for Unsupervised Graph-level Anomaly Detectioncited by 10
  22. 2023GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networkscited by 8
  23. 2024Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Modelscited by 7
  24. 2024Rethinking Independent Cross-Entropy Loss For Graph-Structured Datacited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 5.

18 papers.

Sort:

By area:

  1. 2025A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detectioncited by 24
  2. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputationcited by 16
  3. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  4. 2025Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approachcited by 14
  5. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 13
  6. 2024Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimationcited by 11
  7. 2025Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modelingcited by 9
  8. 2024HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detectioncited by 5
  9. 2025Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Spacecited by 4
  10. 2025Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detectioncited by 2
  11. 2025Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classificationcited by 2
  12. 2025From Pixels to Graphs: Deep Graph-Level Anomaly Detection on Dermoscopic Imagescited by 1
6 more
  1. 2025Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modelingcited by 1
  2. 2026From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detectioncited by 1
  3. 2026Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detectioncited by 0
  4. 2026Graph-Based Fraud Detection with Dual-Path Graph Filteringcited by 0
  5. 2026GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detectioncited by 0
  6. 2026MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systemscited by 0