A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control
This work addresses energy efficiency for resource-limited mobile devices in federated learning, representing an incremental improvement.
The paper tackles the high computation-and-communication costs in wireless federated learning by proposing a two-timescale framework that freezes stabilized parameters and controls transmit power for unstable ones, reducing energy consumption while maintaining convergence, with experimental results showing superiority over benchmarks.
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.