mlsanityData to 7 Oct 2026

Raising the Bar in Graph-level Anomaly Detection

arXiv 2205.13845 ↗First posted 27 May 2022cs.LG cs.AIcited by 45

Not on the map. Why?

Abstract (arXiv)

Graph-level anomaly detection has become a critical topic in diverse areas, such as financial fraud detection and detecting anomalous activities in social networks. While most research has focused on anomaly detection for visual data such as images, where high detection accuracies have been obtained, existing deep learning approaches for graphs currently show considerably worse performance. This paper raises the bar on graph-level anomaly detection, i.e., the task of detecting abnormal graphs in a set of graphs. By drawing on ideas from self-supervised learning and transformation learning, we present a new deep learning approach that significantly improves existing deep one-class approaches by fixing some of their known problems, including hypersphere collapse and performance flip. Experiments on nine real-world data sets involving nine techniques reveal that our method achieves an average performance improvement of 11.8% AUC compared to the best existing approach.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 27 May 2022.

Builds on

17 of 29 references.

References · 17

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  5. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  6. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  7. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  8. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  9. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  10. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  11. 2014Graph-based Anomaly Detection and Description: A Surveycited by 182
  12. 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 116
5 more
  1. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  2. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  3. 2014Propagation Kernelscited by 88
  4. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  5. 2020Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approachcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 15; 2024: 19; 2025: 5; 2026: 3.

45 papers.

Sort:

By area:

  1. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  2. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  3. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  4. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  5. 2022Graph Anomaly Detection with Graph Neural Networks: Current Status and Challengescited by 23
  6. 2024Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Modelscited by 21
  7. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  8. 2024Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmarkcited by 18
  9. 2023Graph-level Anomaly Detection via Hierarchical Memory Networkscited by 16
  10. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  11. 2024Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedycited by 13
  12. 2024UniGAD: Unifying Multi-level Graph Anomaly Detectioncited by 13
33 more
  1. 2023Deep Orthogonal Hypersphere Compression for Anomaly Detectioncited by 12
  2. 2023Deep Anomaly Detection under Labeling Budget Constraintscited by 9
  3. 2023Graph Neural Networks based Log Anomaly Detection and Explanationcited by 8
  4. 2023Model Selection of Anomaly Detectors in the Absence of Labeled Validation Datacited by 8
  5. 2023SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detectioncited by 7
  6. 2023State of the Art and Potentialities of Graph-level Learningcited by 6
  7. 2023Self-Discriminative Modeling for Anomalous Graph Detectioncited by 6
  8. 2026FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-level Anomaly Detectioncited by 6
  9. 2024HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detectioncited by 5
  10. 2023ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approachcited by 4
  11. 2023Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approachcited by 3
  12. 2024Anomaly Detection in Graph Structured Data: A Surveycited by 3
  13. 2024Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detectioncited by 3
  14. 2023Multi-representations Space Separation based Graph-level Anomaly-aware Detectioncited by 2
  15. 2024Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posteriorcited by 2
  16. 2024Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligencecited by 2
  17. 2025SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gapscited by 2
  18. 2025Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detectioncited by 2
  19. 2022AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approachcited by 1
  20. 2023Zero-Shot Anomaly Detection via Batch Normalizationcited by 1
  21. 2024FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Frameworkcited by 1
  22. 2024Graph Pre-Training Models Are Strong Anomaly Detectorscited by 1
  23. 2025From Pixels to Graphs: Deep Graph-Level Anomaly Detection on Dermoscopic Imagescited by 1
  24. 2024A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systemscited by 0
  25. 2024GNN-based Anomaly Detection for Encoded Network Trafficcited by 0
  26. 2024GLADformer: A Mixed Perspective for Graph-level Anomaly Detectioncited by 0
  27. 2024Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learningcited by 0
  28. 2024A Methodological Report on Anomaly Detection on Dynamic Knowledge Graphscited by 0
  29. 2024Hyperedge Anomaly Detection with Hypergraph Neural Networkcited by 0
  30. 2025Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learningcited by 0
  31. 2025DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detectioncited by 0
  32. 2026Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypescited by 0
  33. 2026GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detectioncited by 0