Analog Over‐the‐Air Federated Learning: Design and Analysis
Howard Hua Yang, Zihan Chen, Tony Q. S. Quek · 2023
Federated learning (FL) is envisioned as the bedrock of enabling intelligence in next-generation wireless networks, but the limited spectral resources often restrain its scalability. In light of this challenge, recent researches suggested incorporating analog over-the-air computations into FL systems, to exploit the superposition property of electromagnetic waves for fast aggregation of intermediate parameters and substantially enhance the scalability. This chapter provides a general overview of the analog over-the-air federated learning (AirFL) system. Specifically, we illustrate the general system architecture and highlight the salient feature of AirFL that adopts analog transmissions for fast (but noisy) aggregation of intermediate parameters. Then, we establish a new convergence analysis framework that takes into account the effects of fading and interference noise. Our analysis unveils the impacts from the intrinsic properties of wireless transmissions on the convergence performance of AirFL. The theoretical findings are corroborated by extensive simulations.