Communication Efficient Over-the-Air Federated Learning With Random FLARE Algorithm

Abstract

In this letter, we propose a communication efficient federated learning algorithm, coined random FLARE (R-FLARE), using a novel error compensation method within a framework of random sparsification. In the R-FLARE, all devices sparsify the local gradients using a common set of randomly selected indices to improve communication efficiency with over-the-air computation. To upload local gradients, only the selected gradient elements are compensated by the local errors accumulated due to sparsification, which prevents redundant error compensation. We conduct a theoretical analysis on the convergence of R-FLARE using the l2 norm-based error compensation, which shows that it achieves the same convergence rate as the state-of-the-art algorithms. Numerical results show that the R-FLARE using l1- and l2-norm based error compensations outperform conventional algorithms in test accuracy and training speed. © 2025 IEEE.