Rethinking Federated Learning Over the Air: The Blessing of Scaling Up
Authors:
Preprint
Abstract
Federated learning facilitates collaborative model training across multiple clients while preserving data privacy. However, its performance is often constrained by limited communication resources, particularly in systems supporting a large number of clients. To address this challenge, integrating over-the-air computations into the training process has emerged as a promising solution to alleviate communication bottlenecks. The system significantly increases the number of clients it can support in each communication round by transmitting intermediate parameters via analog signals rather than digital ones. This improvement, however, comes at the cost of channel-induced distortions, such as fading and noise, which affect the aggregated global parameters. To elucidate these effects, this paper develops a theoretical framework to analyze the performance of over-the-air federated learning in large-scale client scenarios. Our analysis reveals three key advantages of scaling up the number of participating clients: (1) Enhanced Privacy: The mutual information between a client's local gradient and the server's aggregated gradient diminishes, effectively reducing privacy leakage. (2) Mitigation of Channel Fading: The channel hardening effect eliminates the impact of small-scale fading in the noisy global gradient. (3) Improved Convergence: Reduced thermal noise and gradient estimation errors benefit the convergence rate. These findings solidify over-the-air model training as a viable approach for federated learning in networks with a large number of clients. The theoretical insights are further substantiated through extensive experimental evaluations.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Over-the-air federated learning: Status quo, open challenges, and future directionsFundamental Research, 2025
- Experimental Demonstration of Over the Air Federated Learning for Cellular Networks2025
- Edge Intelligence Over the Air: Two Faces of Interference in Federated LearningIEEE Communications Magazine, 2023
- Joint Device Selection and Power Control for Wireless Federated LearningIEEE Journal on Selected Areas in Communications, 2022
- Revisiting Analog Over-the-Air Machine Learning: The Blessing and Curse of InterferenceIEEE Journal of Selected Topics in Signal Processing, 2021
- Optimized Power Control Design for Over-the-Air Federated Edge LearningIEEE Journal on Selected Areas in Communications, 2021
- Deep Leakage from Gradients2020
- Privacy for Free: Wireless Federated Learning via Uncoded Transmission With Adaptive Power ControlIEEE Journal on Selected Areas in Communications, 2020
- Federated Learning for Wireless Communications: Motivation, Opportunities, and ChallengesIEEE Communications Magazine, 2020
- Berry–Esseen bounds in the entropic central limit theoremProbability Theory and Related Fields, 2013