Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multitask Active Learning for Graph Anomaly Detection (2401.13210v1)

Published 24 Jan 2024 in cs.LG and cs.SI

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Active learning: A survey. In Data classification, pages 599–634. Chapman and Hall/CRC, 2014.
  2. Active learning for graph embedding. arXiv preprint arXiv:1705.05085, 2017.
  3. Query learning with large margin classifiers. In ICML, volume 20, page 0, 2000.
  4. Can abnormality be detected by graph neural networks. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI), Vienna, Austria, pages 23–29, 2022.
  5. R. Collobert and J. Weston. A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of the 25th international conference on Machine learning, pages 160–167, 2008.
  6. Active anomaly detection via ensembles: Insights, algorithms, and interpretability. arXiv preprint arXiv:1901.08930, 2019.
  7. Incorporating expert feedback into active anomaly discovery. In 2016 IEEE 16th International Conference on Data Mining (ICDM), pages 853–858. IEEE, 2016.
  8. Deep anomaly detection on attributed networks. In Proceedings of the 2019 SIAM International Conference on Data Mining, pages 594–602. SIAM, 2019.
  9. Few-shot network anomaly detection via cross-network meta-learning. In Proceedings of the Web Conference 2021, pages 2448–2456, 2021.
  10. Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In Proceedings of the 29th ACM international conference on information & knowledge management, pages 315–324, 2020.
  11. User preference-aware fake news detection. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2051–2055, 2021.
  12. Active discriminative network representation learning. In IJCAI International Joint Conference on Artificial Intelligence, 2018.
  13. Active learning from positive and unlabeled data. In 2011 IEEE 11th International Conference on Data Mining Workshops, pages 244–250. IEEE, 2011.
  14. Toward supervised anomaly detection. Journal of Artificial Intelligence Research, 46:235–262, 2013.
  15. End-to-end open-set semi-supervised node classification with out-of-distribution detection. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, 2022.
  16. A survey of community detection approaches: From statistical modeling to deep learning. IEEE Transactions on Knowledge and Data Engineering, 35(2):1149–1170, 2021.
  17. T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  18. Deep anomaly detection under labeling budget constraints. In International Conference on Machine Learning, pages 19882–19910. PMLR, 2023.
  19. Enhancing the reliability of out-of-distribution image detection in neural networks. In International Conference on Learning Representations, 2018.
  20. Dagad: Data augmentation for graph anomaly detection. In 2022 IEEE International Conference on Data Mining (ICDM), pages 259–268. IEEE, 2022.
  21. Lscale: Latent space clustering-based active learning for node classification. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 55–70. Springer, 2022.
  22. Bond: Benchmarking unsupervised outlier node detection on static attributed graphs. Advances in Neural Information Processing Systems, 35:27021–27035, 2022.
  23. Pick and choose: a gnn-based imbalanced learning approach for fraud detection. In Proceedings of the web conference 2021, pages 3168–3177, 2021.
  24. Anomaly detection on attributed networks via contrastive self-supervised learning. IEEE transactions on neural networks and learning systems, 33(6):2378–2392, 2021.
  25. Geniepath: Graph neural networks with adaptive receptive paths. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 4424–4431, 2019.
  26. Alleviating the inconsistency problem of applying graph neural network to fraud detection. In Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, pages 1569–1572, 2020.
  27. Comga: Community-aware attributed graph anomaly detection. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pages 657–665, 2022.
  28. Deep active autoencoders for outlier detection. Neural Processing Letters, pages 1–13, 2022.
  29. Opinion spam detection: Using multi-iterative graph-based model. Information processing & management, 57(1):102140, 2020.
  30. Ssd: A unified framework for self-supervised outlier detection. In International Conference on Learning Representations, 2020.
  31. Collective classification in network data. AI magazine, 29(3):93–93, 2008.
  32. B. Settles. Active learning literature survey. University of Wisconsin-Madison Department of Computer Sciences, 2009.
  33. D. B. Skillicorn. Detecting anomalies in graphs. In 2007 IEEE Intelligence and Security Informatics, pages 209–216. IEEE, 2007.
  34. Y. Song and D. Wang. Learning on graphs with out-of-distribution nodes. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 1635–1645, 2022.
  35. Graph posterior network: Bayesian predictive uncertainty for node classification. Advances in Neural Information Processing Systems, 34:18033–18048, 2021.
  36. Rethinking graph neural networks for anomaly detection. In International Conference on Machine Learning, pages 21076–21089. PMLR, 2022.
  37. L. Tang and H. Liu. Relational learning via latent social dimensions. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 817–826, 2009.
  38. A semi-supervised graph attentive network for financial fraud detection. In 2019 IEEE International Conference on Data Mining (ICDM), pages 598–607. IEEE, 2019.
  39. Fdgars: Fraudster detection via graph convolutional networks in online app review system. In Companion proceedings of the 2019 World Wide Web conference, pages 310–316, 2019.
  40. Active learning for graph neural networks via node feature propagation. arXiv preprint arXiv:1910.07567, 2019.
  41. Consisrec: Enhancing gnn for social recommendation via consistent neighbor aggregation. In Proceedings of the 44th international ACM SIGIR conference on Research and development in information retrieval, pages 2141–2145, 2021.
  42. Q. Yu and K. Aizawa. Unsupervised out-of-distribution detection by maximum classifier discrepancy. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9518–9526, 2019.
  43. Meta-aad: Active anomaly detection with deep reinforcement learning. In 2020 IEEE International Conference on Data Mining (ICDM), pages 771–780. IEEE, 2020.
  44. Graph neural network-driven traffic forecasting for the connected internet of vehicles. IEEE Transactions on Network Science and Engineering, 9(5):3015–3027, 2021.
  45. Alg: Fast and accurate active learning framework for graph convolutional networks. In Proceedings of the 2021 International Conference on Management of Data, pages 2366–2374, 2021.
  46. Y. Zhang and Q. Yang. A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering, 34(12):5586–5609, 2021.
  47. Uncertainty aware semi-supervised learning on graph data. Advances in Neural Information Processing Systems, 33:12827–12836, 2020.
  48. Contrastive out-of-distribution detection for pretrained transformers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
  49. Step: Out-of-distribution detection in the presence of limited in-distribution labeled data. Advances in Neural Information Processing Systems, 34:29168–29180, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Wenjing Chang (3 papers)
  2. Kay Liu (14 papers)
  3. Kaize Ding (59 papers)
  4. Philip S. Yu (592 papers)
  5. Jianjun Yu (4 papers)
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - AhaChang/MITIGATE (5 stars)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets