Physical Sciences and Mathematics Commons^™

Unbiased Federated Learning In Energy Harvesting Error-Prone Channels, Zeynep Çakir, Eli̇f Tuğçe Ceran Arslan

Turkish Journal of Electrical Engineering and Computer Sciences

Federated learning (FL) is a communication-efficient and privacy-preserving learning technique for collaborative training of machine learning models on vast amounts of data produced and stored locally on the distributed users. This paper investigates unbiased FL methods that achieve a similar convergence as state-of-the-art methods in scenarios with various constraints like an error-prone channel or intermittent energy availability. For this purpose, we propose FL algorithms that jointly design unbiased user scheduling and gradient weighting according to each user's distinct energy and channel profile. In addition, we exploit a prevalent metric called the age of information (AoI), which quantifies the staleness of …