mlsanityData to 7 Oct 2026

Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation

arXiv 2112.10063 ↗First posted 19 Dec 2021cs.CV cs.AI cs.LGcited by 67

Not on the map. Why?

Abstract (arXiv)

Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs, i.e., graphs that are abnormal in their fine-grained (node-level) or holistic (graph-level) properties, respectively. To tackle this challenge we introduce a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations. The random distillation is achieved by training one GNN to predict another GNN with randomly initialized network weights. Extensive experiments on 16 real-world graph datasets from diverse domains show that our model significantly outperforms seven state-of-the-art models. Code and datasets are available at https://git.io/GLocalKD.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 24 of its 57 references that are in the map. First posted on arXiv 19 Dec 2021.

Builds on

24 of 57 references.

References · 24

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2018Exploration by Random Network Distillationcited by 966
  6. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  7. 2018Deep Learning on Graphs: A Surveycited by 393
  8. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  9. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  10. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  11. 2018Randomized Prior Functions for Deep Reinforcement Learningcited by 218
  12. 2014Graph-based Anomaly Detection and Description: A Surveycited by 182
12 more
  1. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  2. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
  3. 2014Propagation Kernelscited by 88
  4. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  5. 2018Learning Deep Features for One-Class Classificationcited by 76
  6. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  7. 2016Fast Memory-efficient Anomaly Detection in Streaming Heterogeneous Graphscited by 37
  8. 2019Unsupervised Representation Learning by Predicting Random Distancescited by 34
  9. 2018One-Class Adversarial Nets for Fraud Detectioncited by 33
  10. 2019Fence GAN: Towards Better Anomaly Detectioncited by 32
  11. 2020Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approachcited by 20
  12. 2020Semi-supervised Anomaly Detection on Attributed Graphscited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 17; 2024: 25; 2025: 13; 2026: 6.

67 papers.

Sort:

By area:

  1. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  2. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  3. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  4. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 46
  5. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  6. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  7. 2025BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attackscited by 37
  8. 2022Graph Anomaly Detection with Graph Neural Networks: Current Status and Challengescited by 23
  9. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  10. 2024Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Modelscited by 21
  11. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  12. 2024Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmarkcited by 18
38 more
  1. 2024GOODAT: Towards Test-time Graph Out-of-Distribution Detectioncited by 17
  2. 2023Graph-level Anomaly Detection via Hierarchical Memory Networkscited by 16
  3. 2023Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillationcited by 15
  4. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  5. 2024Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedycited by 13
  6. 2024UniGAD: Unifying Multi-level Graph Anomaly Detectioncited by 13
  7. 2023Deep Orthogonal Hypersphere Compression for Anomaly Detectioncited by 12
  8. 2022Functional Anomaly Detection: a Benchmark Studycited by 10
  9. 2023Soft Prompt Decoding for Multilingual Dense Retrievalcited by 10
  10. 2024CVTGAD: Simplified Transformer with Cross-View Attention for Unsupervised Graph-level Anomaly Detectioncited by 10
  11. 2023Graph Neural Networks based Log Anomaly Detection and Explanationcited by 8
  12. 2023SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detectioncited by 7
  13. 2023State of the Art and Potentialities of Graph-level Learningcited by 6
  14. 2023Graph-based Knowledge Distillation: A survey and experimental evaluationcited by 6
  15. 2023Discriminative Graph-level Anomaly Detection via Dual-students-teacher Modelcited by 6
  16. 2023Self-Discriminative Modeling for Anomalous Graph Detectioncited by 6
  17. 2026FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-level Anomaly Detectioncited by 6
  18. 2022Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detectioncited by 5
  19. 2024HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detectioncited by 5
  20. 2023ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approachcited by 4
  21. 2024Anomaly Detection in Graph Structured Data: A Surveycited by 3
  22. 2024Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detectioncited by 3
  23. 2024HGOE: Hybrid External and Internal Graph Outlier Exposure for Graph Out-of-Distribution Detectioncited by 3
  24. 2025Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detectioncited by 3
  25. 2023Pattern Mining for Anomaly Detection in Graphs: Application to Fraud in Public Procurementcited by 2
  26. 2023Multi-representations Space Separation based Graph-level Anomaly-aware Detectioncited by 2
  27. 2023HRGCN: Heterogeneous Graph-level Anomaly Detection with Hierarchical Relation-augmented Graph Neural Networkscited by 2
  28. 2024Harnessing Collective Structure Knowledge in Data Augmentation for Graph Neural Networkscited by 2
  29. 2024Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligencecited by 2
  30. 2025SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gapscited by 2
  31. 2025Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detectioncited by 2
  32. 2025Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classificationcited by 2
  33. 2022AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approachcited by 1
  34. 2024FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Frameworkcited by 1
  35. 2024Subgraph2vec: A random walk-based algorithm for embedding knowledge graphscited by 1
  36. 2024FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detectioncited by 1
  37. 2024Extreme Value Modelling of Feature Residuals for Anomaly Detection in Dynamic Graphscited by 1
  38. 2024Graph Pre-Training Models Are Strong Anomaly Detectorscited by 1

50 most cited of 67 All 67 (JSON)