FedHelo: Hierarchical Federated Learning With Loss-Based-Heterogeneity in Wireless Networks
- 26 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (6) , 6066-6079
Abstract
Hierarchical federated learning (HFL) in wireless networks significantly saves communication resources due to edge aggregation conducted in edge mobile computing (MEC) servers. Taking into account the spatially correlated characteristics of data in wireless networks, in this paper, we analyze the performance of HFL with hybrid data distributions, i.e. intra-MEC independent and identically distributed (IID) and inter-MEC non-IID data samples. We derive the upper bound of the difference between the achieved loss and the minimum one, which reveals the impacts of data heterogeneity and global aggregation frequency on the performance of HFL. On this basis, we propose an algorithm named FedHelo which optimizes the aggregation weights and edge/global aggregation frequencies under the constraints of training delay and clients' energy consumption. Our experiments i) verify the obtained theoretical results; ii) demonstrate the performance improvement achieved by FedHelo with the optimal aggregation weights and training/aggregation frequencies, especially in the scenario with high data heterogeneity; and iii) show the preference for edge aggregation in the scenario with a tight delay or client's energy constraint.Keywords
Funding Information
- National Natural Science Foundation of China (62271150)
This publication has 41 references indexed in Scilit:
- Federated learning on non-IID data: A surveyNeurocomputing, 2021
- Client Selection for Federated Learning With Non-IID Data in Mobile Edge ComputingIEEE Access, 2021
- Enabling AI in Future Wireless Networks: A Data Life Cycle PerspectiveIEEE Communications Surveys & Tutorials, 2020
- Federated learning with hierarchical clustering of local updates to improve training on non-IID data2020
- Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data2020
- Client-Edge-Cloud Hierarchical Federated Learning2020
- Hierarchical Federated Learning ACROSS Heterogeneous Cellular Networks2020
- Federated Learning in Mobile Edge Networks: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2020
- Deep Residual Learning for Image Recognition2016
- Global solutions to nonconvex optimization of 4th-order polynomial and log-sum-exp functionsJournal of Global Optimization, 2014