mlsanityData to 7 Oct 2026

Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks

arXiv 2205.04816 ↗First posted 10 May 2022cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Detecting abnormal nodes from attributed networks is of great importance in many real applications, such as financial fraud detection and cyber security. This task is challenging due to both the complex interactions between the anomalous nodes with other counterparts and their inconsistency in terms of attributes. This paper proposes a self-supervised learning framework that jointly optimizes a multi-view contrastive learning-based module and an attribute reconstruction-based module to more accurately detect anomalies on attributed networks. Specifically, two contrastive learning views are firstly established, which allow the model to better encode rich local and global information related to the abnormality. Motivated by the attribute consistency principle between neighboring nodes, a masked autoencoder-based reconstruction module is also introduced to identify the nodes which have large reconstruction errors, then are regarded as anomalies. Finally, the two complementary modules are integrated for more accurately detecting the anomalous nodes. Extensive experiments conducted on five benchmark datasets show our model outperforms current state-of-the-art models.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 10 May 2022.

Builds on

16 of 30 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2018Deep Graph Infomaxcited by 1,101
  5. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  6. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  7. 2020Deep Graph Contrastive Representation Learningcited by 535
  8. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  9. 2019Diffusion Improves Graph Learningcited by 414
  10. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  11. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
  12. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
4 more
  1. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 150
  2. 2021Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detectioncited by 67
  3. 2019SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networkscited by 37
  4. 2016Scalable Anomaly Ranking of Attributed Neighborhoodscited by 33

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 8; 2025: 8; 2026: 2.

28 papers.

Sort:

By area:

  1. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 54
  2. 2023Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detectioncited by 43
  3. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  4. 2023PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detectioncited by 25
  5. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  6. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  7. 2022ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awarenesscited by 8
  8. 2023Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detectioncited by 7
  9. 2024Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detectioncited by 7
  10. 2025Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspectivecited by 7
  11. 2023Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learningcited by 6
  12. 2024Towards Cross-domain Few-shot Graph Anomaly Detectioncited by 5
16 more
  1. 2025Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learningcited by 4
  2. 2025Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detectioncited by 3
  3. 2026GCTAM: Global and Contextual Truncated Affinity Combined Maximization Model For Unsupervised Graph Anomaly Detectioncited by 3
  4. 2024UMGAD: Unsupervised Multiplex Graph Anomaly Detectioncited by 2
  5. 2025Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphscited by 2
  6. 2022AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approachcited by 1
  7. 2023Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graphcited by 1
  8. 2023MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly Detectioncited by 1
  9. 2024SCALA: Sparsification-based Contrastive Learning for Anomaly Detection on Attributed Networkscited by 1
  10. 2024Topology Reorganized Graph Contrastive Learning with Mitigating Semantic Driftcited by 1
  11. 2025Structural-Temporal Coupling Anomaly Detection with Dynamic Graph Transformercited by 1
  12. 2026AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detectioncited by 1
  13. 2024Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detectioncited by 0
  14. 2025Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detectioncited by 0
  15. 2025Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspectivecited by 0
  16. 2025Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detectioncited by 0