|
|
联邦学习综述
|
Abstract:
随着隐私保护和机器学习数据量需求的攀升，传统机器学习面临诸多挑战。联邦学习作为一种去中心化的分布式机器学习策略受到了广泛的关注。联邦学习通常由中央服务器发起，诸多形态、性能各异的边缘客户端设备共同参与。在联邦学习过程中，客户端设备不需要将私有数据共享给任何一方，从而起到隐私保护以及防止数据泄露的作用。不仅如此，联邦学习具备分布式机器学习的特点，可以有效发挥边缘设备的存储资源和计算资源。本文系统性地回顾了联邦学习的基本概念，并对联邦学习的实际应用和发展作了凝结性介绍，总结了联邦学习当前面临的数据异质性、掉队者效应、隐私保护等挑战，以促进联邦学习的发展和应用。
With the increasing demand for privacy protection and large-scale machine learning datasets, traditional machine learning faces numerous challenges. As a decentralized and distributed machine learning paradigm, Federated Learning (FL) has garnered widespread attention. FL is typically initiated by a central server, with various different edge client devices participating collaboratively. During the FL process, client devices do not need to share their private data with any party, thereby ensuring privacy protection and preventing data leakage. Moreover, FL leverages the characteristics of distributed machine learning, effectively utilizing the storage and computational resources of edge devices. This paper systematically reviews the fundamental concepts of FL and provides a concise overview of its practical applications and developments. Additionally, it summarizes key challenges in FL, including data heterogeneity, straggler effects, and privacy protection, to promote further advancements and applications of FL.
| [1] | McMahan, B., Moore, E., Ramage, D., et al. (2017) Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv: 1602.05629. |
| [2] | Byrd, D. and Polychroniadou, A. (2020) Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications. Proceedings of the First ACM International Conference on AI in Finance, New York, 15-16 October 2020, 1-9. https://doi.org/10.1145/3383455.3422562 |
| [3] | Xu, J., Glicksberg, B.S., Su, C., Walker, P., Bian, J. and Wang, F. (2020) Federated Learning for Healthcare Informatics. Journal of Healthcare Informatics Research, 5, 1-19. https://doi.org/10.1007/s41666-020-00082-4 |
| [4] | Muhammad, K., Wang, Q., O’Reilly-Morgan, D., Tragos, E., Smyth, B., Hurley, N., et al. (2020) FedFast: Going Beyond Average for Faster Training of Federated Recommender Systems. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 6-10 July 2020, 1234-1242. https://doi.org/10.1145/3394486.3403176 |
| [5] | Nguyen, D.C., Ding, M., Pathirana, P.N., Seneviratne, A., Li, J. and Vincent Poor, H. (2021) Federated Learning for Internet of Things: A Comprehensive Survey. IEEE Communications Surveys & Tutorials, 23, 1622-1658. https://doi.org/10.1109/comst.2021.3075439 |
| [6] | Zeng, T., Semiari, O., Chen, M., Saad, W. and Bennis, M. (2022) Federated Learning on the Road Autonomous Controller Design for Connected and Autonomous Vehicles. IEEE Transactions on Wireless Communications, 21, 10407-10423. https://doi.org/10.1109/twc.2022.3183996 |
| [7] | Li, T., Sahu, A.K., Zaheer, M., et al. (2020) Federated Optimization in Heterogeneous Networks. Machine Learning and Systems (MLSys), 2, 429-450. |
| [8] | Karimi Reddy, S.P., Kale, S., Mohri, M., et al. (2020) SCAFFOLD: Stochastic Controlled Averaging for Federated Learning. arXiv: 1910.06378. |
| [9] | Acar D A E, Zhao Y, Navarro R M, et al. (2021) Federated Learning Based on Dynamic Regularization. arXiv: 2111.04263. |
| [10] | Tan, A.Z., Yu, H., Cui, L. and Yang, Q. (2023) Towards Personalized Federated Learning. IEEE Transactions on Neural Networks and Learning Systems, 34, 9587-9603. https://doi.org/10.1109/tnnls.2022.3160699 |
| [11] | Liang, P.P., Liu, T., Ziyin, L., et al. (2019) Think Locally, Act Globally: Federated Learning with Local and Global Representations. https://arxiv.org/abs/2001.01523 |
| [12] | Chen, H.Y. and Chao, W.L. (2022) On Bridging Generic and Personalized Federated Learning for Image Classification. arXiv: 2107.00778. |
| [13] | Oh, J., Kim, S. and Yun, S.Y. (2022) FedBABU: Towards Enhanced Representation for Federated Image Classification. arXiv: 2106.06042. |
| [14] | Chen, C., Feng, X., Zhou, J., Yin, J. and Zheng, X. (2023) Federated Large Language Model: A Position Paper. arXiv: 2307.08925. |
| [15] | Wang, Z. and Hu, Q. (2021) Blockchain-Based Federated Learning: A Comprehensive Survey. arXiv: 2110.02182. |
| [16] | Li, Q., Diao, Y., Chen, Q. and He, B. (2022) Federated Learning on Non-IID Data Silos: An Experimental Study. 2022 IEEE 38th International Conference on Data Engineering (ICDE), Kuala Lumpur, 9-12 May 2022, 965-978. https://doi.org/10.1109/icde53745.2022.00077 |
| [17] | Chai, Z., Chen, Y., Zhao, L., Cheng, Y. and Rangwala, H. (2020) FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data. |
| [18] | Wei, K., Li, J., Ding, M., Ma, C., Yang, H.H., Farokhi, F., et al. (2020) Federated Learning with Differential Privacy: Algorithms and Performance Analysis. IEEE Transactions on Information Forensics and Security, 15, 3454-3469. https://doi.org/10.1109/tifs.2020.2988575 |
| [19] | Wibawa, F., Catak, F.O., Kuzlu, M., Sarp, S. and Cali, U. (2022) Homomorphic Encryption and Federated Learning Based Privacy-Preserving CNN Training: COVID-19 Detection Use-Case. EICC 2022: Proccedings of the European Interdisciplinary Cybersecurity Conference, Barcelona, 15-16 June 2022, 85-90. https://doi.org/10.1145/3528580.3532845 |
