mlsanityData to 7 Oct 2026

Rethinking Graph Neural Networks for Anomaly Detection

arXiv 2205.15508 ↗First posted 31 May 2022cs.LG eess.SPcited by 185

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are widely applied for graph anomaly detection. As one of the key components for GNN design is to select a tailored spectral filter, we take the first step towards analyzing anomalies via the lens of the graph spectrum. Our crucial observation is the existence of anomalies will lead to the `right-shift' phenomenon, that is, the spectral energy distribution concentrates less on low frequencies and more on high frequencies. This fact motivates us to propose the Beta Wavelet Graph Neural Network (BWGNN). Indeed, BWGNN has spectral and spatial localized band-pass filters to better handle the `right-shift' phenomenon in anomalies. We demonstrate the effectiveness of BWGNN on four large-scale anomaly detection datasets. Our code and data are released at https://github.com/squareRoot3/Rethinking-Anomaly-Detection

Key facts. Cited by 185 papers in the map (data through 7 Oct 2026). Builds on 28 of its 58 references that are in the map. First posted on arXiv 31 May 2022.

Builds on

28 of 58 references.

References · 28

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  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. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2019Simplifying Graph Convolutional Networkscited by 1,470
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  10. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  11. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  12. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
16 more
  1. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  2. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  3. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 150
  4. 2019Graph Wavelet Neural Networkcited by 131
  5. 2013From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviewscited by 107
  6. 2017Learning Structural Node Embeddings Via Diffusion Waveletscited by 97
  7. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 81
  8. 2020Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networkscited by 57
  9. 2018Diffusion Scattering Transforms on Graphscited by 43
  10. 2021AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filtercited by 43
  11. 2018Outlier Aware Network Embedding for Attributed Networkscited by 29
  12. 2020Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failurecited by 27
  13. 2021Deconvolutional Networks on Graph Datacited by 16
  14. 2021Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filteringcited by 14
  15. 2020Geometric Scattering Attention Networkscited by 5
  16. 2015Compactly Supported One-cyclic Wavelets Derived from Beta Distributionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 36; 2024: 54; 2025: 39; 2026: 49.

185 papers.

Sort:

By area:

  1. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147
  2. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 84
  3. 2024ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphscited by 83
  4. 2023Energy Transformercited by 69
  5. 2024Parameter-Efficient Fine-Tuning with Discrete Fourier Transformcited by 67
  6. 2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 57
  7. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 54
  8. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  9. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 46
  10. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  11. 2023GAD-NR: Graph Anomaly Detection via Neighborhood Reconstructioncited by 44
  12. 2023Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detectioncited by 43
38 more
  1. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  2. 2024Alleviating Structural Distribution Shift in Graph Anomaly Detectioncited by 31
  3. 2023Inductive Graph Unlearningcited by 30
  4. 2024ProG: A Graph Prompt Learning Benchmarkcited by 29
  5. 2023SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biasescited by 27
  6. 2024Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Promptscited by 24
  7. 2025A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detectioncited by 24
  8. 2023ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detectioncited by 23
  9. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  10. 2024Partitioning Message Passing for Graph Fraud Detectioncited by 21
  11. 2023Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrumcited by 20
  12. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  13. 2023Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationcited by 19
  14. 2024Anomaly Detection in Dynamic Graphs: A Comprehensive Surveycited by 18
  15. 2023Alleviating Over-smoothing for Unsupervised Sentence Representationcited by 16
  16. 2023A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignmentcited by 16
  17. 2022Semi-Supervised Hierarchical Graph Classificationcited by 15
  18. 2023Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transportcited by 15
  19. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  20. 2024Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptationcited by 15
  21. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  22. 2023Knowledge Graph Completion with Counterfactual Augmentationcited by 13
  23. 2024UniGAD: Unifying Multi-level Graph Anomaly Detectioncited by 13
  24. 2022Handling Missing Data via Max-Entropy Regularized Graph Autoencodercited by 12
  25. 2025Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Timecited by 12
  26. 2023Improving Generalizability of Graph Anomaly Detection Models via Data Augmentationcited by 11
  27. 2023Open-Set Graph Anomaly Detection via Normal Structure Regularisationcited by 11
  28. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  29. 2024SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detectioncited by 11
  30. 2024Weakly Supervised Anomaly Detection via Knowledge-Data Alignmentcited by 10
  31. 2025Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detectioncited by 10
  32. 2025FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detectioncited by 10
  33. 2022ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awarenesscited by 8
  34. 2024Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matchingcited by 8
  35. 2025Dual-channel Heterophilic Message Passing for Graph Fraud Detectioncited by 8
  36. 2026Tabular Foundation Models are Strong Graph Anomaly Detectorscited by 8
  37. 2026From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detectioncited by 8
  38. 2022Mul-GAD: a semi-supervised graph anomaly detection framework via aggregating multi-view informationcited by 7

50 most cited of 185 All 185 (JSON)