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

FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework (2402.12761v1)

Published 20 Feb 2024 in cs.LG and cs.CR

Abstract: Graph anomaly detection (GAD) aims to identify anomalous graphs that significantly deviate from other ones, which has raised growing attention due to the broad existence and complexity of graph-structured data in many real-world scenarios. However, existing GAD methods usually execute with centralized training, which may lead to privacy leakage risk in some sensitive cases, thereby impeding collaboration among organizations seeking to collectively develop robust GAD models. Although federated learning offers a promising solution, the prevalent non-IID problems and high communication costs present significant challenges, particularly pronounced in collaborations with graph data distributed among different participants. To tackle these challenges, we propose an effective federated graph anomaly detection framework (FGAD). We first introduce an anomaly generator to perturb the normal graphs to be anomalous, and train a powerful anomaly detector by distinguishing generated anomalous graphs from normal ones. Then, we leverage a student model to distill knowledge from the trained anomaly detector (teacher model), which aims to maintain the personality of local models and alleviate the adverse impact of non-IID problems. Moreover, we design an effective collaborative learning mechanism that facilitates the personalization preservation of local models and significantly reduces communication costs among clients. Empirical results of the GAD tasks on non-IID graphs compared with state-of-the-art baselines demonstrate the superiority and efficiency of the proposed FGAD method.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. A review on outlier/anomaly detection in time series data. ACM Computing Surveys (CSUR) 54, 3 (2021), 1–33.
  2. Jinyu Cai and Jicong Fan. 2022. Perturbation learning based anomaly detection. Advances in Neural Information Processing Systems 35 (2022).
  3. Anomaly detection: A survey. ACM Computing Surveys (CSUR) 41, 3 (2009), 1–58.
  4. Ailin Deng and Bryan Hooi. 2021. Graph neural network-based anomaly detection in multivariate time series. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4027–4035.
  5. Few-shot network anomaly detection via cross-network meta-learning. In Proceedings of the Web Conference. 2448–2456.
  6. Federated learning of generative image priors for MRI reconstruction. IEEE Transactions on Medical Imaging (2022).
  7. Matthias Fey and Jan Eric Lenssen. 2019. Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428 (2019).
  8. Federated graph machine learning: A survey of concepts, techniques, and applications. ACM SIGKDD Explorations Newsletter 24, 2 (2022), 32–47.
  9. Alleviating structural distribution shift in graph anomaly detection. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. 357–365.
  10. Advances and open problems in federated learning. Foundations and Trends® in Machine Learning 14, 1–2 (2021), 1–210.
  11. Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).
  12. Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016).
  13. Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations.
  14. Meta-har: Federated representation learning for human activity recognition. In Proceedings of the Web Conference. 912–922.
  15. Cutpaste: Self-supervised learning for anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9664–9674.
  16. Model-contrastive federated learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10713–10722.
  17. Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine 37, 3 (2020), 50–60.
  18. Federated optimization in heterogeneous networks. Proceedings of Machine Learning and Systems 2 (2020), 429–450.
  19. Federated graph neural networks: Overview, techniques and challenges. arXiv preprint arXiv:2202.07256 (2022).
  20. Time series anomaly detection with adversarial reconstruction networks. IEEE Transactions on Knowledge and Data Engineering 35, 4 (2022), 4293–4306.
  21. Deep anomaly detection for time-series data in industrial IoT: A communication-efficient on-device federated learning approach. IEEE Internet of Things Journal 8, 8 (2020), 6348–6358.
  22. Anomaly detection on attributed networks via contrastive self-supervised learning. IEEE Transactions on Neural Networks and Learning Systems 33, 6 (2021), 2378–2392.
  23. Deep graph-level anomaly detection by glocal knowledge distillation. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. 704–714.
  24. A comprehensive survey on graph anomaly detection with deep learning. IEEE Transactions on Knowledge and Data Engineering (2021).
  25. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the International Conference on Artificial Intelligence and Statistics. PMLR, 1273–1282.
  26. TUDataset: A collection of benchmark datasets for learning with graphs. In Proceedings of the ICML Workshop on Graph Representation Learning and Beyond. arXiv:2007.08663 www.graphlearning.io
  27. Deep learning for anomaly detection: A review. ACM Computing Surveys (CSUR) 54, 2 (2021), 1–38.
  28. Raising the Bar in Graph-level Anomaly Detection. In Proceedings of the International Joint Conference on Artificial Intelligence. 2196–2203. https://doi.org/10.24963/ijcai.2022/305
  29. Deep one-class classification. In Proceedings of the International Conference on Machine Learning. PMLR, 4393–4402.
  30. Federated learning on non-iid graphs via structural knowledge sharing. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 9953–9961.
  31. Rethinking graph neural networks for anomaly detection. In Proceedings of the International Conference on Machine Learning. PMLR, 21076–21089.
  32. Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008), 2579–2605.
  33. A system for time series feature extraction in federated learning. In Proceedings of the ACM International Conference on Information & Knowledge Management. 5024–5028.
  34. Federatedscope-gnn: Towards a unified, comprehensive and efficient package for federated graph learning. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4110–4120.
  35. Hierarchical personalized federated learning for user modeling. In Proceedings of the Web Conference. 957–968.
  36. Federated graph classification over non-iid graphs. Advances in Neural Information Processing Systems 34 (2021), 18839–18852.
  37. How powerful are graph neural networks?. In Proceedings of the International Conference on Learning Representations.
  38. Label-efficient self-supervised federated learning for tackling data heterogeneity in medical imaging. IEEE Transactions on Medical Imaging (2023).
  39. Characterizing impacts of heterogeneity in federated learning upon large-scale smartphone data. In Proceedings of the Web Conference. 935–946.
  40. Dual-discriminative graph neural network for imbalanced graph-level anomaly detection. Advances in Neural Information Processing Systems 35 (2022), 24144–24157.
  41. Federated graph learning–a position paper. arXiv preprint arXiv:2105.11099 (2021).
  42. Lingxiao Zhao and Leman Akoglu. 2021. On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights. Big Data (2021).
  43. Chenyi Zhuang and Qiang Ma. 2018. Dual graph convolutional networks for graph-based semi-supervised classification. In Proceedings of the World Wide Web Conference. 499–508.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Jinyu Cai (13 papers)
  2. Yunhe Zhang (4 papers)
  3. Zhoumin Lu (2 papers)
  4. Wenzhong Guo (23 papers)
  5. See-Kiong Ng (103 papers)
Citations (1)
View on Semantic Scholar

Summary

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

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

Tweets