mlsanityData to 14 Oct 2026

PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection

arXiv 2310.11676 ↗First posted 18 Oct 2023cs.LG cs.AIcited by 25

Not on the map. Why?

Abstract (arXiv)

Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous nodes from graph-structured data in various domains such as medicine, social networks, and e-commerce. However, challenges have arisen due to the diversity of anomalies and the dearth of labeled data. Existing methodologies - reconstruction-based and contrastive learning - while effective, often suffer from efficiency issues, stemming from their complex objectives and elaborate modules. To improve the efficiency of GAD, we introduce a simple method termed PREprocessing and Matching (PREM for short). Our approach streamlines GAD, reducing time and memory consumption while maintaining powerful anomaly detection capabilities. Comprising two modules - a pre-processing module and an ego-neighbor matching module - PREM eliminates the necessity for message-passing propagation during training, and employs a simple contrastive loss, leading to considerable reductions in training time and memory usage. Moreover, through rigorous evaluations of five real-world datasets, our method demonstrated robustness and effectiveness. Notably, when validated on the ACM dataset, PREM achieved a 5% improvement in AUC, a 9-fold increase in training speed, and sharply reduce memory usage compared to the most efficient baseline.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 41 of its 59 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

41 of 59 references.

References · 41

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  5. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  7. 2018Deep Graph Infomaxcited by 1,106
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  9. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  10. 2020Contrastive Learning with Hard Negative Samplescited by 628
  11. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  12. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
29 more
  1. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  2. 2019Diffusion Improves Graph Learningcited by 414
  3. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  4. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  5. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 177
  6. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  7. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  8. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  9. 2020AnomalyDAE: Dual autoencoder for anomaly detection on attributed networkscited by 82
  10. 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
  11. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  12. 2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 69
  13. 2021Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detectioncited by 67
  14. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  15. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 55
  16. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  17. 2019SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networkscited by 37
  18. 2016Scalable Anomaly Ranking of Attributed Neighborhoodscited by 33
  19. 2021Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networkscited by 31
  20. 2022MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initializationcited by 31
  21. 2022Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networkscited by 28
  22. 2023Learning Strong Graph Neural Networks with Weak Informationcited by 25
  23. 2023Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphscited by 25
  24. 2022DAGAD: Data Augmentation for Graph Anomaly Detectioncited by 20
  25. 2021Towards Graph Self-Supervised Learning with Contrastive Adjusted Zoomingcited by 15
  26. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  27. 2022Unifying Graph Contrastive Learning with Flexible Contextual Scopescited by 14
  28. 2021Relevance-Aware Anomalous Users Detection in Social Network via Graph Neural Networkcited by 12
  29. 2021Learning Graph Neural Networks with Positive and Unlabeled Nodescited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 9; 2025: 8; 2026: 8.

25 papers.

Sort:

By area:

  1. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 48
  2. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  3. 2025BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attackscited by 38
  4. 2025A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detectioncited by 24
  5. 2024Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmarkcited by 18
  6. 2024Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformationcited by 15
  7. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  8. 2024SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detectioncited by 11
  9. 2026From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detectioncited by 8
  10. 2024Towards Cross-domain Few-shot Graph Anomaly Detectioncited by 5
  11. 2026Towards Anomaly Detection on Relational Datacited by 5
  12. 2025Semi-supervised Graph Anomaly Detection via Robust Homophily Learningcited by 4
13 more
  1. 2025Str-GCL: Structural Commonsense Driven Graph Contrastive Learningcited by 3
  2. 2026CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detectioncited by 3
  3. 2024UMGAD: Unsupervised Multiplex Graph Anomaly Detectioncited by 2
  4. 2024MEATRD: Multimodal Anomalous Tissue Region Detection Enhanced with Spatial Transcriptomicscited by 2
  5. 2025Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphscited by 2
  6. 2026When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systemscited by 1
  7. 2025Robust Anomaly Detection with Graph Neural Networks using Controllabilitycited by 0
  8. 2025Combining Euclidean and Hyperbolic Representations for Node-level Anomaly Detectioncited by 0
  9. 2025A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detectioncited by 0
  10. 2026Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detectioncited by 0
  11. 2026DDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combinecited by 0
  12. 2026RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detectioncited by 0
  13. 2026SIM: Subspace Interaction-based Method for Token-Level Text Anomaly Detectioncited by 0