mlsanityData to 14 Oct 2026

Multitask Active Learning for Graph Anomaly Detection

arXiv 2401.13210 ↗First posted 24 Jan 2024cs.LG cs.SIcited by 7

Not on the map. Why?

Abstract (arXiv)

In the web era, graph machine learning has been widely used on ubiquitous graph-structured data. As a pivotal component for bolstering web security and enhancing the robustness of graph-based applications, the significance of graph anomaly detection is continually increasing. While Graph Neural Networks (GNNs) have demonstrated efficacy in supervised and semi-supervised graph anomaly detection, their performance is contingent upon the availability of sufficient ground truth labels. The labor-intensive nature of identifying anomalies from complex graph structures poses a significant challenge in real-world applications. Despite that, the indirect supervision signals from other tasks (e.g., node classification) are relatively abundant. In this paper, we propose a novel MultItask acTIve Graph Anomaly deTEction framework, namely MITIGATE. Firstly, by coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies. Secondly, MITIGATE quantifies the informativeness of nodes by the confidence difference across tasks, allowing samples with conflicting predictions to provide informative yet not excessively challenging information for subsequent training. Finally, to enhance the likelihood of selecting representative nodes that are distant from known patterns, MITIGATE adopts a masked aggregation mechanism for distance measurement, considering both inherent features of nodes and current labeled status. Empirical studies on four datasets demonstrate that MITIGATE significantly outperforms the state-of-the-art methods for anomaly detection. Our code is publicly available at: https://github.com/AhaChang/MITIGATE.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 24 Jan 2024.

Builds on

29 of 49 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  3. 2017A Survey on Multi-Task Learningcited by 840
  4. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  5. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 250
  6. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 187
  7. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 177
  8. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 151
  9. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  10. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  11. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 82
  12. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 80
17 more
  1. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  2. 2021User Preference-aware Fake News Detectioncited by 79
  3. 2014Toward Supervised Anomaly Detectioncited by 73
  4. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 71
  5. 2018GeniePath: Graph Neural Networks with Adaptive Receptive Pathscited by 66
  6. 2021Few-shot Network Anomaly Detection via Cross-network Meta-learningcited by 64
  7. 2021A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learningcited by 55
  8. 2017Active Learning for Graph Embeddingcited by 54
  9. 2021ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregationcited by 39
  10. 2019Active Learning for Graph Neural Networks via Node Feature Propagationcited by 37
  11. 2020Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learningcited by 34
  12. 2023Learning on Graphs with Out-of-Distribution Nodescited by 29
  13. 2022DAGAD: Data Augmentation for Graph Anomaly Detectioncited by 20
  14. 2019Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learningcited by 9
  15. 2023Deep Anomaly Detection under Labeling Budget Constraintscited by 9
  16. 2020LSCALE: Latent Space Clustering-Based Active Learning for Node Classificationcited by 8
  17. 2016Active Learning from Positive and Unlabeled Datacited by 5

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 2.

7 papers.

  1. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  2. 2024Uncertainty in Graph Neural Networks: A Surveycited by 23
  3. 2024LEGO-Learn: Label-Efficient Graph Open-Set Learningcited by 10
  4. 2025Few-Shot Graph Out-of-Distribution Detection with LLMscited by 6
  5. 2024Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglementcited by 3
  6. 2024TGTOD: A Global Temporal Graph Transformer for Outlier Detection at Scalecited by 1
  7. 2025Metric Matters: A Formal Evaluation of Similarity Measures in Active Learning for Cyber Threat Intelligencecited by 0