Federated Learning in Wireless IoT Networks: A New Algorithm for Device Selection and Communication Resource Allocation

• Renan R. de Oliveira UFG / IFG
• Rogério S. e Silva UFG / IFG
• Leandro A. Freitas IFG
• Antonio Oliveira-Jr UFG / Fraunhofer Portugal AICOS

DOI: https://doi.org/10.5753/sbrc.2024.1267

Abstract

Federated Learning (FL) allows devices to train a global machine learning model without sharing data. In the context of wireless networks, limited resources and the inherent unreliable nature of the transmission medium introduce delays and errors that compromise the regularity of updating the global model. Therefore, this work proposes a new FL algorithm called DFed-w_Opt that considers both the requirements of federated training and a wireless network within the scope of the Internet of Things. To minimize the loss function, DFed-w_Opt selects a subset of devices with the largest amount of data for training local models. Then, DFed-w_Opt maximizes the probability of successful transmission of models meeting a communication latency and energy consumption policy. The simulation results show that DFed-w_Opt increases the number of transmissions and the accuracy of the global model compared to other strategies in the literature.

References

Amannejad, Y. (2020). Building and Evaluating Federated Models for Edge Computing. In 2020 16th International Conference on Network and Service Management (CNSM), pages 1–5.

Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Parcollet, T., and Lane, N. D. (2020). Flower: A Friendly Federated Learning Research Framework. CoRR, abs/2007.14390.

Cao, X., Başar, T., Diggavi, S., Eldar, Y. C., Letaief, K. B., Poor, H. V., and Zhang, J. (2023). Communication-Efficient Distributed Learning: An Overview. IEEE Journal on Selected Areas in Communications, 41(4):851–873.

Chen, H., Huang, S., Zhang, D., Xiao, M., Skoglund, M., and Poor, H. V. (2022). Federated Learning Over Wireless IoT Networks With Optimized Communication and Resources. IEEE Internet of Things Journal, 9(17):16592–16605.

Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., and Cui, S. (2021). A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks. IEEE Transactions on Wireless Communications, 20(1):269–283.

Cho, Y. J., Wang, J., and Joshi, G. (2020). Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies. CoRR, abs/2010.01243.

Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., and He, B. (2021). A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection. IEEE Transactions on Knowledge and Data Engineering, PP:1–1.

McMahan, H. B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2016). Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv.

Tran, N. H., Bao, W., Zomaya, A., Nguyen, M. N. H., and Hong, C. S. (2019). Federated Learning over Wireless Networks: Optimization Model Design and Analysis. In IEEE INFOCOM 2019 - IEEE Conference on Computer Communications, pages 1387–1395.

Yang, Z., Chen, M., Wong, K.-K., Poor, H. V., and Cui, S. (2022). Federated Learning for 6G: Applications, Challenges, and Opportunities. Engineering, 8:33–41.

Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., and Chandra, V. (2022). Federated Learning with Non-IID Data. arXiv.

Zhu, G., Wang, Y., and Huang, K. (2020). Broadband Analog Aggregation for Low-Latency Federated Edge Learning. IEEE Transactions on Wireless Communications, 19(1):491–506.