|
|
一种自适应学习率的联邦学习算法
|
Abstract:
当前人们越来越重视个人信息的保护，联邦学习由于本地训练，不用上传数据而当作一种保护数据隐私的机器学习框架被提出。但是面对现实世界的数据异质性设备时，联邦学习出现全局模型性能下降，收敛速度降低等问题。针对这个现象，本文聚焦于联邦学习的聚合阶段，通过理论分析，结合联邦学习全局损失的收敛上界和更新过程提出了Fedalr算法。该算法通过使用动量方法估计全局梯度，自适应计算出局部梯度的学习率来优化聚合模型，目的是提高了联邦学习的收敛速度和全局模型性能。另外，我们还验证了算法收敛性。最后通过不同种类统计异质性数据的仿真实验，证明了该算法比起当前基准算法性能更优秀，性能最多优化提升了30.74%。
With growing concerns over personal information protection, federated learning has emerged as a privacy-preserving machine learning framework by enabling local training without data uploads. However, in real-world scenarios with heterogeneous data and devices, federated learning faces challenges such as degraded global model performance and slower convergence. To address this, we focus on the aggregation phase of federated learning and propose the Fedalr algorithm, based on theoretical analysis of the convergence upper bound and update process of the global loss. Fedalr employs momentum methods to estimate global gradients and adaptively computes local gradient learning rates to optimize the aggregated model, aiming to improve convergence speed and global model performance. We also provide a theoretical proof of the algorithm’s convergence. Experimental results on various statistically heterogeneous datasets demonstrate that Fedalr outperforms existing baseline algorithms, achieving performance improvements of up to 30.74%.
| [1] | McMahan, B., Moore, E., Ramage, D., Hampson, S. and Agüera y Arcas, B. (2017) Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, 20-22 April 2017, 1273-1282. |
| [2] | Wang, H., Kaplan, Z., Niu, D. and Li, B. (2020) Optimizing Federated Learning on Non-IID Data with Reinforcement Learning. IEEE INFOCOM 2020—IEEE Conference on Computer Communications, Toronto, 6-9 July 2020, 1698-1707. https://doi.org/10.1109/infocom41043.2020.9155494 |
| [3] | Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D. and Chandra, V. (2018) Federated Learning with Non-IID Data. |
| [4] | Li, X., Huang, K., Yang, W., Wang, S. and Zhang, Z. (2020) On the Convergence of FedAvg on Non-IID Data. 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, 26-30 April 2020, 26 p. |
| [5] | Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S.J., Stich, S.U. and Suresh, A.T. (2019) SCAFFOLD: Stochastic Con-trolled Averaging for On-Device Federated Learning. |
| [6] | Marfoq, O., Neglia, G., Bellet, A., Kameni, L. and Vidal, R. (2021) Federated Multi-Task Learning under a Mixture of Distributions. Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6-14 December 2021, 15434-15447. |
| [7] | Zhu, Z., Hong, J. and Zhou, J. (2021) Data-Free Knowledge Distillation for Heterogeneous Federated Learning. Proceedings of the 38th International Conference on Machine Learning, Vol. 139, 12878-12889. |
| [8] | Zheng, W., Yan, L., Gou, C. and Wang, F. (2020) Federated Meta-Learning for Fraudulent Credit Card Detection. Proceedings of the 29th International Joint Conference on Artificial Intelligence, Yokohama, 11-17 July 2020, 4654-4660. https://doi.org/10.24963/ijcai.2020/642 |
| [9] | Liu, Y., Kang, Y., Xing, C., Chen, T. and Yang, Q. (2020) A Secure Federated Transfer Learning Framework. IEEE Intelligent Systems, 35, 70-82. https://doi.org/10.1109/mis.2020.2988525 |
| [10] | Chen, F., Luo, M., Dong, Z., et al. (2018) Federated Meta-Learning with Fast Convergence and Efficient Communication. |
| [11] | Liu, Y., Kang, Y., Xing, C., Chen, T. and Yang, Q. (2020) Federated Transfer Learning with Adversarial Adaptation for Non-IID Data. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 4696-4703. |
| [12] | Chen, Y., Qin, X., Wang, J., Yu, C. and Gao, W. (2020) Fedhealth: A Federated Transfer Learning Framework for Wearable Healthcare. IEEE Intelligent Systems, 35, 83-93. https://doi.org/10.1109/mis.2020.2988604 |
| [13] | Rizk, E., Vlaski, S. and Sayed, A.H. (2022) Federated Learning under Importance Sampling. IEEE Transactions on Signal Processing, 70, 5381-5396. https://doi.org/10.1109/tsp.2022.3210365 |
| [14] | Duan, M., Liu, D., Ji, X., Liu, R., Liang, L., Chen, X., et al. (2021) Fedgroup: Efficient Federated Learning via Decomposed Similarity-Based Clustering. 2021 IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), New York, 30 September-3 October 2021, 228-237. https://doi.org/10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00042 |
| [15] | Wu, H. and Wang, P. (2021) Fast-Convergent Federated Learning with Adaptive Weighting. IEEE Transactions on Cognitive Communications and Networking, 7, 1078-1088. https://doi.org/10.1109/tccn.2021.3084406 |
| [16] | Hu, Z., Shaloudegi, K., Zhang, G. and Yu, Y. (2022) Federated Learning Meets Multi-Objective Optimization. IEEE Transactions on Network Science and Engineering, 9, 2039-2051. https://doi.org/10.1109/tnse.2022.3169117 |
| [17] | Li, T., Sanjabi, M., Beirami, A. and Smith, V. (2020) Fair Resource Allocation in Federated Learning. 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, 26-30 April 2020, 27 p. |
| [18] | Fallah, A., Mokhtari, A. and Ozdaglar, A.E. (2020) Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach. Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6-12 December 2020, 12 p. |
| [19] | Collins, L., Hassani, H., Mokhtari, A. and Shakkottai, S. (2021) Exploiting Shared Representations for Personalized Federated Learning. Proceedings of the 38th International Conference on Machine Learning, Vol. 139, 2089-2099. |
| [20] | Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A. and Smith, V. (2020) Federated Optimization in Heterogeneous Networks. Proceedings of the 3rd Conference on Machine Learning and Systems, MLSys 2020, Austin, 2-4 March 2020, 22 p. |
| [21] | Li, Q., He, B. and Song, D. (2021) Model-Contrastive Federated Learning. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 19-25 June 2021, 10713-10722. https://doi.org/10.1109/cvpr46437.2021.01057 |
| [22] | Dinh, C.T., Tran, N.H. and Nguyen, T.D. (2020) Personalized Federated Learning with Moreau Envelopes. Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6-12 December 2020, 12 p. |
| [23] | 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 |
