Abstract
Recently, federated Learning (FL) has been widely used to protect clients’ data privacy in distributed applications, and heterogeneous data and model poisoning are two critical challenges to attack. To tackle the first challenge that data of each client is usually not independent or identically distributed, personalized FL (PFL) or clustered FL, which can be seen as a cluster-wise PFL method to learn multiple models across clients or clusters. To detect the anomaly clients or outliers, local outlier factor is a popular method based on the density of data points. Therefore, a nested bi-level optimization objective is constructed, and an algorithm of PFL with robust clustering called FedPRC is proposed to detect outliers and maintain state-of-the-art performance. The breakdown point of FedPRC can be at least 0.5. Our experimental analysis has demonstrated effectiveness and superior performance in comparison with baselines in multiple benchmark datasets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ana, L.F., Jain, A.K.: Robust data clustering. In: Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, p. II. IEEE (2003)
Arthur, D., Vassilvitskii, S.: K-means++: the advantages of careful seeding. Technical report, Stanford (2006)
Bhagoji, A.N., Chakraborty, S., Mittal, P., Calo, S.: Analyzing federated learning through an adversarial lens. In: International Conference on Machine Learning, pp. 634–643. PMLR (2019)
Blanchard, P., El Mhamdi, E.M., Guerraoui, R., Stainer, J.: Machine learning with adversaries: Byzantine tolerant gradient descent. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93–104 (2000)
Brunet-Saumard, C., Genetay, E., Saumard, A.: K-bMOM: a robust Lloyd-type clustering algorithm based on bootstrap median-of-means. Comput. Stat. Data Anal. 167, 107370 (2022)
Caldas, S., et al.: Leaf: a benchmark for federated settings. arXiv preprint arXiv:1812.01097 (2018)
Chen, F., Luo, M., Dong, Z., Li, Z., He, X.: Federated meta-learning with fast convergence and efficient communication. arXiv preprint arXiv:1802.07876 (2018)
Chen, X., Liu, C., Li, B., Lu, K., Song, D.: Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526 (2017)
Cheng, G., Chadha, K., Duchi, J.: Fine-tuning is fine in federated learning. arXiv preprint arXiv:2108.07313 (2021)
Cohen, G., Afshar, S., Tapson, J., Van Schaik, A.: EMNIST: extending MNIST to handwritten letters. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2921–2926. IEEE (2017)
Collins, L., Hassani, H., Mokhtari, A., Shakkottai, S.: Exploiting shared representations for personalized federated learning. In: International Conference on Machine Learning, pp. 2089–2099. PMLR (2021)
Damaskinos, G., El-Mhamdi, E.M., Guerraoui, R., Guirguis, A., Rouault, S.: Aggregathor: Byzantine machine learning via robust gradient aggregation. Proc. Mach. Learn. Syst. 1, 81–106 (2019)
Davé, R.N., Krishnapuram, R.: Robust clustering methods: a unified view. IEEE Trans. Fuzzy Syst. 5(2), 270–293 (1997)
Deshpande, A., Kacham, P., Pratap, R.: Robust \(k\)-means++. In: Conference on Uncertainty in Artificial Intelligence, pp. 799–808. PMLR (2020)
Apple Differential Privacy Team: Learning with privacy at scale (2017). https://machinelearning.apple.com/research/learning-with-privacy-at-scale
Fallah, A., Mokhtari, A., Ozdaglar, A.: Personalized federated learning with theoretical guarantees: a model-agnostic meta-learning approach. In: Advances in Neural Information Processing Systems, vol. 33, pp. 3557–3568 (2020)
García-Escudero, L.A., Gordaliza, A., Matrán, C., Mayo-Iscar, A.: A general trimming approach to robust cluster analysis. Ann. Stat. 36(3), 1324–1345 (2008)
García-Escudero, L.A., Gordaliza, A., Matrán, C., Mayo-Iscar, A.: A review of robust clustering methods. Adv. Data Anal. Classif. 4(2), 89–109 (2010)
Ghosh, A., Chung, J., Yin, D., Ramchandran, K.: An efficient framework for clustered federated learning. arXiv preprint arXiv:2006.04088 (2020)
Ghosh, A., Hong, J., Yin, D., Ramchandran, K.: Robust federated learning in a heterogeneous environment. arXiv preprint arXiv:1906.06629 (2019)
Guha, S., Rastogi, R., Shim, K.: Rock: a robust clustering algorithm for categorical attributes. Inf. Syst. 25(5), 345–366 (2000)
He, C., et al.: FedCV: a federated learning framework for diverse computer vision tasks. arXiv preprint arXiv:2111.11066 (2021)
Jallepalli, D., Ravikumar, N.C., Badarinath, P.V., Uchil, S., Suresh, M.A.: Federated learning for object detection in autonomous vehicles. In: 2021 IEEE Seventh International Conference on Big Data Computing Service and Applications (BigDataService), pp. 107–114. IEEE (2021)
Li, T., Hu, S., Beirami, A., Smith, V.: Ditto: fair and robust federated learning through personalization. In: International Conference on Machine Learning, pp. 6357–6368. PMLR (2021)
Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. arXiv preprint arXiv:1812.06127 (2018)
Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smithy, V.: FedDANE: a federated newton-type method. In: 2019 53rd Asilomar Conference on Signals, Systems, and Computers, pp. 1227–1231. IEEE (2019)
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE ICCV, pp. 3730–3738 (2015)
Long, G., Shen, T., Tan, Y., Gerrard, L., Clarke, A., Jiang, J.: Federated learning for privacy-preserving open innovation future on digital health. In: Chen, F., Zhou, J. (eds.) Humanity Driven AI, pp. 113–133. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-72188-6_6
Luo, J., et al.: Real-world image datasets for federated learning. arXiv preprint arXiv:1910.11089 (2019)
Ma, J., Long, G., Zhou, T., Jiang, J., Zhang, C.: On the convergence of clustered federated learning. arXiv preprint arXiv:2202.06187 (2022)
Mansour, Y., Mohri, M., Ro, J., Suresh, A.T.: Three approaches for personalization with applications to federated learning. arXiv preprint arXiv:2002.10619 (2020)
McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)
Muniyandi, A.P., Rajeswari, R., Rajaram, R.: Network anomaly detection by cascading K-means clustering and C4.5 decision tree algorithm. Procedia Eng. 30, 174–182 (2012)
Nichol, A., Schulman, J.: Reptile: a scalable metalearning algorithm. arXiv preprint arXiv:1803.02999 (2018)
Paul, D., Chakraborty, S., Das, S.: Robust principal component analysis: a median of means approach. arXiv preprint arXiv:2102.03403 (2021)
Rieke, N., et al.: The future of digital health with federated learning. NPJ Digit. Med. 3(1), 1–7 (2020)
Sattler, F., Müller, K.R., Samek, W.: Clustered federated learning: model-agnostic distributed multi-task optimization under privacy constraints. arXiv preprint arXiv:1910.01991 (2019)
Sattler, F., Müller, K.R., Samek, W.: Clustered federated learning: model-agnostic distributed multitask optimization under privacy constraints. IEEE Trans. Neural Netw. Learn. Syst. 32, 3710–3722 (2020)
Shamsian, A., Navon, A., Fetaya, E., Chechik, G.: Personalized federated learning using hypernetworks. In: International Conference on Machine Learning, pp. 9489–9502. PMLR (2021)
Smith, V., Chiang, C.K., Sanjabi, M., Talwalkar, A.S.: Federated multi-task learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Tan, Y., et al.: FedProto: federated prototype learning over heterogeneous devices. arXiv preprint arXiv:2105.00243 (2021)
Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., Khazaeni, Y.: Federated learning with matched averaging. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=BkluqlSFDS
Xie, M., et al.: Multi-center federated learning. arXiv preprint arXiv:2108.08647 (2021)
Xu, J., Glicksberg, B.S., Su, C., Walker, P., Bian, J., Wang, F.: Federated learning for healthcare informatics. J. Healthcare Inform. Res. 5(1), 1–19 (2021)
Yang, M.S., Lai, C.Y., Lin, C.Y.: A robust EM clustering algorithm for gaussian mixture models. Pattern Recogn. 45(11), 3950–3961 (2012)
Yang, M.S., Wu, K.L.: A similarity-based robust clustering method. IEEE Trans. Pattern Anal. Mach. Intell. 26(4), 434–448 (2004)
Zheng, Z., Zhou, Y., Sun, Y., Wang, Z., Liu, B., Li, K.: Applications of federated learning in smart cities: recent advances, taxonomy, and open challenges. Connect. Sci. 34(1), 1–28 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, J., Xie, M., Long, G. (2022). Personalized Federated Learning with Robust Clustering Against Model Poisoning. In: Chen, W., Yao, L., Cai, T., Pan, S., Shen, T., Li, X. (eds) Advanced Data Mining and Applications. ADMA 2022. Lecture Notes in Computer Science(), vol 13726. Springer, Cham. https://doi.org/10.1007/978-3-031-22137-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-22137-8_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22136-1
Online ISBN: 978-3-031-22137-8
eBook Packages: Computer ScienceComputer Science (R0)