Update Estimation and Scheduling for Over-the-Air Federated Learning with Energy Harvesting Devices
This work addresses energy efficiency and data heterogeneity in federated learning for wireless devices, but it appears incremental as it builds on existing scheduling methods.
The paper tackles the problem of over-the-air federated learning with energy harvesting devices under heterogeneous data and fading channels by proposing user scheduling strategies to select diverse users, resulting in improved learning performance through reduced redundancy and energy conservation.
We study over-the-air (OTA) federated learning (FL) for energy harvesting devices with heterogeneous data distribution over wireless fading multiple access channel (MAC). To address the impact of low energy arrivals and data heterogeneity on global learning, we propose user scheduling strategies. Specifically, we develop two approaches: 1) entropy-based scheduling for known data distributions and 2) least-squares-based user representation estimation for scheduling with unknown data distributions at the parameter server. Both methods aim to select diverse users, mitigating bias and enhancing convergence. Numerical and analytical results demonstrate improved learning performance by reducing redundancy and conserving energy.