A Two-Timescale Approach for Wireless Federated Learning With Parameter Freezing and Power Control
- 4 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (9) , 8841-8855
Abstract
Federated learning (FL) enables distributed devices to train a shared machine learning (ML) model collaboratively while protecting their data privacy. However, the resource-limited mobile devices suffer from intensive computation-and-communication costs of model parameters. In this paper, we observe the phenomenon that the model parameters tend to be stabilized long before convergence during training process. Based on this observation, we propose a two-timescale FL framework by joint optimization of freezing stabilized parameters and controlling transmit power for the unstable parameters to balance the energy consumption and convergence. First, we analyze the impact of model parameter freezing and unreliable transmission on the convergence rate. Next, we formulate a two-timescale optimization problem of parameter freezing percentage and transmit power to minimize the model convergence error subject to the energy budget. To solve this problem, we decompose it into parallel sub-problems and decompose each sub-problem into two different timescales problems using the Lyapunov optimization method. The optimal parameter freezing and power control strategies are derived in an online fashion. Experimental results demonstrate the superiority of the proposed scheme compared with the benchmark schemes.Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- Federated Learning and Meta Learning: Approaches, Applications, and DirectionsIEEE Communications Surveys & Tutorials, 2023
- Client Selection for Federated Bayesian LearningIEEE Journal on Selected Areas in Communications, 2023
- Quantized Federated Learning Under Transmission Delay and Outage ConstraintsIEEE Journal on Selected Areas in Communications, 2021
- Low-Latency Federated Learning Over Wireless Channels With Differential PrivacyIEEE Journal on Selected Areas in Communications, 2021
- Distributed Learning in Wireless Networks: Recent Progress and Future ChallengesIEEE Journal on Selected Areas in Communications, 2021
- A Comprehensive Survey on Training Acceleration for Large Machine Learning Models in IoTIEEE Internet of Things Journal, 2021
- Artificial Neural Networks-Based Machine Learning for Wireless Networks: A TutorialIEEE Communications Surveys & Tutorials, 2019
- Application of Machine Learning in Wireless Networks: Key Techniques and Open IssuesIEEE Communications Surveys & Tutorials, 2019
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Convex Optimization2004