Communication-Efficient Zero-Order and First-Order Federated Learning Methods Over Wireless Networks
IEEE Transactions on Signal Processing · 2026 · 74 · 2706-2723
DOI: 10.1109/tsp.2026.3697131 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Signal Processing, 2026. Verfasst von Mohamad Assaad und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben.
Abstract (Originalsprache)
Federated Learning (FL) is an emerging learning framework that enables edge devices to collaboratively train ML models without sharing their local data. However, FL faces a significant challenge due to the high amount of information that must be exchanged between devices and the aggregator in the training phase, which can exceed the limited capacity of wireless systems. In this paper, two communication-efficient FL methods are considered, where communication overhead is reduced by communicating scalar values instead of long vectors and by allowing a high number of users to send information simultaneously. The first approach employs a zero-order optimization technique with a two-point gradient estimator, while the second involves a first-order gradient computation strategy. The novelty lies in leveraging channel information in the learning algorithms, hence eliminating the need for additional resources to acquire channel state information (CSI) and to remove its impact, as well as in considering asynchronous devices. We provide a rigorous analytical framework for the two methods, deriving convergence guarantees and establishing appropriate performance bounds.
Zitieren
APA
Assaad, M., Nehme, Z., & Debbah, M. (2026). Communication-Efficient Zero-Order and First-Order Federated Learning Methods Over Wireless Networks. IEEE Transactions on Signal Processing, 74, 2706-2723. https://doi.org/10.1109/tsp.2026.3697131
Vancouver
Assaad M, Nehme Z, Debbah M. Communication-Efficient Zero-Order and First-Order Federated Learning Methods Over Wireless Networks. IEEE Transactions on Signal Processing. 2026;74:2706-2723. doi:10.1109/tsp.2026.3697131
BibTeX
@article{Assaad2026,
author = {Assaad, Mohamad and Nehme, Zeinab and Debbah, Merouane},
title = {Communication-Efficient Zero-Order and First-Order Federated Learning Methods Over Wireless Networks},
journal = {IEEE Transactions on Signal Processing},
year = {2026},
volume = {74},
pages = {2706--2723},
doi = {10.1109/tsp.2026.3697131}
}
EUVIMED