mlsanityData to 14 Oct 2026

Few-shot Network Anomaly Detection via Cross-network Meta-learning

arXiv 2102.11165 ↗First posted 22 Feb 2021cs.LGcited by 64

Not on the map. Why?

Abstract (arXiv)

Network anomaly detection aims to find network elements (e.g., nodes, edges, subgraphs) with significantly different behaviors from the vast majority. It has a profound impact in a variety of applications ranging from finance, healthcare to social network analysis. Due to the unbearable labeling cost, existing methods are predominately developed in an unsupervised manner. Nonetheless, the anomalies they identify may turn out to be data noises or uninteresting data instances due to the lack of prior knowledge on the anomalies of interest. Hence, it is critical to investigate and develop few-shot learning for network anomaly detection. In real-world scenarios, few labeled anomalies are also easy to be accessed on similar networks from the same domain as of the target network, while most of the existing works omit to leverage them and merely focus on a single network. Taking advantage of this potential, in this work, we tackle the problem of few-shot network anomaly detection by (1) proposing a new family of graph neural networks -- Graph Deviation Networks (GDN) that can leverage a small number of labeled anomalies for enforcing statistically significant deviations between abnormal and normal nodes on a network; and (2) equipping the proposed GDN with a new cross-network meta-learning algorithm to realize few-shot network anomaly detection by transferring meta-knowledge from multiple auxiliary networks. Extensive evaluations demonstrate the efficacy of the proposed approach on few-shot or even one-shot network anomaly detection.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Builds on 23 of its 65 references that are in the map. First posted on arXiv 22 Feb 2021.

Builds on

23 of 65 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2016Matching Networks for One Shot Learningcited by 2,255
  7. 2019Simplifying Graph Convolutional Networkscited by 1,477
  8. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  9. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  10. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  11. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 250
  12. 2014Graph-based Anomaly Detection and Description: A Surveycited by 183
11 more
  1. 2019Deep Anomaly Detection with Deviation Networkscited by 153
  2. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 151
  3. 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
  4. 2019Transferring Robustness for Graph Neural Network Against Poisoning Attackscited by 58
  5. 2019Spam Review Detection with Graph Convolutional Networkscited by 57
  6. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  7. 2019SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networkscited by 37
  8. 2018Outlier Aware Network Embedding for Attributed Networkscited by 29
  9. 2020Semi-supervised Anomaly Detection on Attributed Graphscited by 18
  10. 2021Isometric Propagation Network for Generalized Zero-shot Learningcited by 18
  11. 2019Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graphcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 18; 2023: 18; 2024: 17; 2025: 5; 2026: 2.

64 papers.

Sort:

By area:

  1. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  2. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  3. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  4. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  5. 2022PyGOD: A Python Library for Graph Outlier Detectioncited by 32
  6. 2022Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignmentcited by 31
  7. 2023SAD: Semi-Supervised Anomaly Detection on Dynamic Graphscited by 28
  8. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  9. 2021Meta Propagation Networks for Graph Few-shot Semi-supervised Learningcited by 25
  10. 2022Graph Anomaly Detection with Graph Neural Networks: Current Status and Challengescited by 23
  11. 2023Weakly Supervised Anomaly Detection: A Surveycited by 22
  12. 2022DAGAD: Data Augmentation for Graph Anomaly Detectioncited by 20
38 more
  1. 2022JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networkscited by 15
  2. 2022Graph Learning for Anomaly Analytics: Algorithms, Applications, and Challengescited by 15
  3. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  4. 2022Deep Graph Learning for Anomalous Citation Detectioncited by 14
  5. 2024SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learningcited by 14
  6. 2022From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approachcited by 13
  7. 2022Few-Shot Learning on Graphscited by 11
  8. 2023BeMap: Balanced Message Passing for Fair Graph Neural Networkcited by 11
  9. 2023Improving Generalizability of Graph Anomaly Detection Models via Data Augmentationcited by 11
  10. 2023RoSAS: Deep Semi-Supervised Anomaly Detection with Contamination-Resilient Continuous Supervisioncited by 11
  11. 2023Open-Set Graph Anomaly Detection via Normal Structure Regularisationcited by 11
  12. 2024Graph Domain Adaptation: Challenges, Progress and Prospectscited by 11
  13. 2024Weakly Supervised Anomaly Detection via Knowledge-Data Alignmentcited by 10
  14. 2022Supervised Graph Contrastive Learning for Few-shot Node Classificationcited by 9
  15. 2023Federated Few-shot Learningcited by 9
  16. 2021Meta-Learning with Graph Neural Networks: Methods and Applicationscited by 7
  17. 2024Multitask Active Learning for Graph Anomaly Detectioncited by 7
  18. 2024A Survey of Few-Shot Learning for Biomedical Time Seriescited by 7
  19. 2024Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detectioncited by 7
  20. 2022Anomaly Detection in Multiplex Dynamic Networks: from Blockchain Security to Brain Disease Predictioncited by 6
  21. 2023A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledgecited by 6
  22. 2023Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detectioncited by 6
  23. 2024A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learningcited by 6
  24. 2024AnomalyLLM: Few-shot Anomaly Edge Detection for Dynamic Graphs using Large Language Modelscited by 5
  25. 2024Towards Cross-domain Few-shot Graph Anomaly Detectioncited by 5
  26. 2023Enhance Diffusion to Improve Robust Generalizationcited by 3
  27. 2024Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Modelscited by 3
  28. 2025Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defensescited by 3
  29. 2022Graph Perceiver IO: A General Architecture for Graph Structured Datacited by 2
  30. 2022Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regressioncited by 2
  31. 2022GENIUS: A Novel Solution for Subteam Replacement with Clustering-based Graph Neural Networkcited by 2
  32. 2023Few-shot Weakly-supervised Cybersecurity Anomaly Detectioncited by 2
  33. 2023Effective Illicit Account Detection on Large Cryptocurrency MultiGraphscited by 2
  34. 2025Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphscited by 2
  35. 2022Convolutional Ensembling based Few-Shot Defect Detection Techniquecited by 1
  36. 2023Zero-Shot Anomaly Detection via Batch Normalizationcited by 1
  37. 2023MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly Detectioncited by 1
  38. 2023Label-based Graph Augmentation with Metapath for Graph Anomaly Detectioncited by 1

50 most cited of 64 All 64 (JSON)