mlsanityData to 14 Oct 2026

UniGAD: Unifying Multi-level Graph Anomaly Detection

arXiv 2411.06427 ↗First posted 10 Nov 2024cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Graph Anomaly Detection (GAD) aims to identify uncommon, deviated, or suspicious objects within graph-structured data. Existing methods generally focus on a single graph object type (node, edge, graph, etc.) and often overlook the inherent connections among different object types of graph anomalies. For instance, a money laundering transaction might involve an abnormal account and the broader community it interacts with. To address this, we present UniGAD, the first unified framework for detecting anomalies at node, edge, and graph levels jointly. Specifically, we develop the Maximum Rayleigh Quotient Subgraph Sampler (MRQSampler) that unifies multi-level formats by transferring objects at each level into graph-level tasks on subgraphs. We theoretically prove that MRQSampler maximizes the accumulated spectral energy of subgraphs (i.e., the Rayleigh quotient) to preserve the most significant anomaly information. To further unify multi-level training, we introduce a novel GraphStitch Network to integrate information across different levels, adjust the amount of sharing required at each level, and harmonize conflicting training goals. Comprehensive experiments show that UniGAD outperforms both existing GAD methods specialized for a single task and graph prompt-based approaches for multiple tasks, while also providing robust zero-shot task transferability. All codes can be found at https://github.com/lllyyq1121/UniGAD.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 45 of its 70 references that are in the map. First posted on arXiv 10 Nov 2024.

Builds on

45 of 70 references.

References · 45

  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. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  7. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  8. 2016Cross-stitch Networks for Multi-task Learningcited by 467
  9. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  10. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
  11. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 250
  12. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
33 more
  1. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  2. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  3. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 187
  4. 2014Graph-based Anomaly Detection and Description: A Surveycited by 183
  5. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 177
  6. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
  7. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 164
  8. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 151
  9. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 148
  10. 2023PRODIGY: Enabling In-context Learning Over Graphscited by 98
  11. 2023A Survey of Graph Meets Large Language Model: Progress and Future Directionscited by 85
  12. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 82
  13. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  14. 2021Deep Graph-level Anomaly Detection by Glocal Knowledge Distillationcited by 67
  15. 2018GeniePath: Graph Neural Networks with Adaptive Receptive Pathscited by 66
  16. 2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 58
  17. 2019Spam Review Detection with Graph Convolutional Networkscited by 57
  18. 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignmentcited by 56
  19. 2019Semi-Supervised Graph Classification: A Hierarchical Graph Perspectivecited by 55
  20. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 55
  21. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  22. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  23. 2023GAD-NR: Graph Anomaly Detection via Neighborhood Reconstructioncited by 45
  24. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  25. 2023MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphscited by 40
  26. 2019SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networkscited by 37
  27. 2022Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalizationcited by 35
  28. 2023SGL-PT: A Strong Graph Learner with Graph Prompt Tuningcited by 35
  29. 2024ProG: A Graph Prompt Learning Benchmarkcited by 29
  30. 2022DAGAD: Data Augmentation for Graph Anomaly Detectioncited by 20
  31. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  32. 2022Mul-GAD: a semi-supervised graph anomaly detection framework via aggregating multi-view informationcited by 7
  33. 2023Revisiting Graph Contrastive Learning for Anomaly Detectioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 7.

14 papers.

Sort:

By area:

  1. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 14
  2. 2025Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learningcited by 5
  3. 2026Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detectioncited by 2
  4. 2026Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detectioncited by 2
  5. 2025Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactionscited by 1
  6. 2025Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detectioncited by 0
  7. 2025Context-Based Fake News Detection using Graph Based Approach: ACOVID-19 Use-casecited by 0
  8. 2025FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervisioncited by 0
  9. 2025Spatio-Temporal Graphs Beyond Grids: Benchmark for Maritime Anomaly Detectioncited by 0
  10. 2026Controlled Dynamics Attractor Transformercited by 0
  11. 2026A Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware Contrastive Learningcited by 0
  12. 2026OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attackscited by 0
2 more
  1. 2026FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detectioncited by 0
  2. 2026Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphscited by 0