Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks
Abstract
Over-the-air computation has emerged as a scalable and efficient solution for deploying federated learning algorithms in wireless networks by exploiting waveform superposition for simultaneous model aggregation. Most existing work struggles with heterogeneous fading channels. These approaches either enforce unbiased updates from all devices or allow partial device contributions, requiring careful tuning of the convergence bound to mitigate bias under specific fading models. However, the former significantly amplifies receiver noise due to the weakest channel, whereas the latter is sensitive to fading model mismatch and converges only to a biased objective. To tackle these challenges, we propose FedOAG, which employs algorithmic components to automatically satisfy energy constraints via gradient normalization and evenly mix devices' updates through implicit gossiping. Importantly, FedOAG does not require transmission from all devices, nor does it rely on a specific fading model or knowledge of time-varying statistical channel distributions. We show that FedOAG converges to a stationary point of an unbiased non-convex objective at the best possible rate O(1/√T) for any stochastic first-order method. We corroborate our analysis with numerical experiments over dynamic wireless conditions on real-world datasets.
Versions
Related
- A Joint Power-Privacy Control Framework for Decentralized Learning over Heterogeneous Wireless Multicasting Networks
- Large Stepsizes Federated Learning on Logistic Regression with Linearly Separable Data: The Case of Heterogeneous Devices
- Mathematical Analysis of Backdoor-Induced Melanoma Risk in Modality-Heterogeneous Federated Learning
- PA-CFL: Privacy-Preserving Adaptive Clustered Federated Learning Under Heterogeneous Data
- Adaptive Beam Hopping and Power Control for Dual-Layer Over-the-Air Online Federated Learning in LEO Satellite Networks
BibTeX
@misc{xiang2026overtheair,
title = {{Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks}},
author = {Ming Xiang and Nicolò Michelusi and Yonina C. Eldar and Lili Su},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.32832},
eprint = {2609.32832},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.32832},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks
AU - Ming Xiang
AU - Nicolò Michelusi
AU - Yonina C. Eldar
AU - Lili Su
PY - 2026
DA - 2026/09/26
PB - arXiv
DO - 10.48550/arxiv.2609.32832
UR - https://arxiv.org/abs/2609.32832
AB - Over-the-air computation has emerged as a scalable and efficient solution for deploying federated learning algorithms in wireless networks by exploiting waveform superposition for simultaneous model aggregation. Most existing work struggles with heterogeneous fading channels. These approaches either enforce unbiased updates from all devices or allow partial device contributions, requiring careful tuning of the convergence bound to mitigate bias under specific fading models. However, the former significantly amplifies receiver noise due to the weakest channel, whereas the latter is sensitive to fading model mismatch and converges only to a biased objective. To tackle these challenges, we propose FedOAG, which employs algorithmic components to automatically satisfy energy constraints via gradient normalization and evenly mix devices' updates through implicit gossiping. Importantly, FedOAG does not require transmission from all devices, nor does it rely on a specific fading model or knowledge of time-varying statistical channel distributions. We show that FedOAG converges to a stationary point of an unbiased non-convex objective at the best possible rate O(1/√T) for any stochastic first-order method. We corroborate our analysis with numerical experiments over dynamic wireless conditions on real-world datasets.
ER -