A Survey on Optimization of Federated Learning Based on Edge-Cloud Collaboration
DOI:
https://doi.org/10.61173/50fdsd79Keywords:
Edge-cloud collaboration, Federated learning, Communication protocols, Optimization MethodsAbstract
In order to address issues including resource limitations, data heterogeneity, and computational inefficiency, this study explores the optimization of lightweight federated learning (FL) in edge-cloud collaborative contexts. Due to non-IID data distributions, high communication costs, and restricted device capabilities, traditional federated learning frameworks perform below expectations in edge environments. This study analyzes the background and challenges, elaborates on definitions and theories, emphasizes the classification of federated learning and finally provides several optimization solutions. The objective is to provide strong support for federated learning applications in resource-constrained scenarios while efficiently increasing the operational efficiency of federated learning systems in edge-cloud environments. The results lay the groundwork for future studies on scalable and effective distributed learning systems by highlighting the promise of lightweight FL in applications like smart healthcare and industrial Internet of Things (IoT). In particular, it underscores the need for adaptive mechanisms that dynamically adjust computation and communication strategies based on the capabilities of edge devices.
References
[1] T. Li, A. K. Sahu, A. Talwalkar and V. Smith. Federated Learning: Challenges, Methods, and Future Directions. IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50-60, May 2020.
[2] W. Y. B. Lim et al. Federated Learning in Mobile Edge Networks: A Comprehensive Survey. IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 2031-2063, 2020.
[3] Z. Lu, H. Pan, Y. Dai, X. Si and Y. Zhang. Federated Learning with Non-IID Data: A Survey. IEEE Internet of Things Journal, vol. 11, no. 11, pp. 19188-19209, 1 June1, 2024.
[4] McMahan, H. B. et al. Communication-Efficient Learning of Deep Networks from Decentralized Data. International Conference on Artificial Intelligence and Statistics (2016).
[5] Bao, G., Guo, P. Federated learning in cloud-edge collaborative architecture: key technologies, applications and challenges.” J Cloud Comp 11, 94, 2022.
[6] Liu, Yang, et al. “Vertical Federated Learning: Concepts, Advances, and Challenges.” IEEE Transactions on Automatic Control 36.7(2024):20.
[7] Saha, Sudipan, and T. Ahmad. Federated transfer learning: Concept and applications. Intelligenza Artificiale 15.1, 2021:35- 44.
[8] Kairouz, Edited By: Peter, and H. B. Mcmahan. Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning 14.1, 2021.
[9] Huang, W., Li, T., Wang, D., Du, S., Zhang, J., & Huang, T. Fairness and accuracy in horizontal federated learning. Information Sciences: An International Journal, 589, 2022.
[10] Liu, W., Wang, Y., Li, K. et al. Ftmoe. A Federated Transfer Model Based on Mixture-of-Experts for Heterogeneous Image Classification. Cluster Comput 28, 165, 2025.
[11] Yang, Qiang, et al. Federated Machine Learning: Concept and Applications. ACM Transactions on Intelligent Systems and Technology 10.2(2019):1-19.
[12] Zhao, Yuchen, P. Barnaghi, and H. Haddadi. Multimodal Federated Learning on IoT Data. 2021.
[13] Cremonesi, Francesco, et al. The need for multimodal health data modeling: A practical approach for a federatedlearning healthcare platform. Journal of biomedical informatics. 104338, 2023.
[14] Yu Q, Liu Y, Wang Y, et al. Multimodal federated learning via contrastive representation ensemble. arXiv preprint arXiv:2302.08888, 2023.
[15] Ye, Yunfan, et al. EdgeFed: Optimized Federated Learning Based on Edge Computing. IEEE Access 8(2020):209191- 209198.
[16] Wang, Shiqiang, et al. Adaptive Federated Learning in Resource Constrained Edge Computing Systems. Selected Areas in Communications, IEEE Journal on (J-SAC) 37.6(2019):17.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
