Saved in:
Bibliographic Details
Main Authors: Ma, Xiaoyan, Zehtabi, Shahryar, Kim, Taejoon, Brinton, Christopher G.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.20277
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909757120446464
author Ma, Xiaoyan
Zehtabi, Shahryar
Kim, Taejoon
Brinton, Christopher G.
author_facet Ma, Xiaoyan
Zehtabi, Shahryar
Kim, Taejoon
Brinton, Christopher G.
contents This paper investigates an OFDM-based over-the-air federated learning (OTA-FL) system, where multiple mobile devices, e.g., unmanned aerial vehicles (UAVs), transmit local machine learning (ML) models to a central parameter server (PS) for global model aggregation. The high mobility of local devices results in imperfect channel estimation, leading to a misalignment problem, i.e., the model parameters transmitted from different local devices do not arrive at the central PS simultaneously. Moreover, the mobility introduces time-varying uploading channels, which further complicates the aggregation process. All these factors collectively cause distortions in the OTA-FL training process which are underexplored. To quantify these effects, we first derive a closed-form expression for a single-round global model update in terms of these channel imperfections. We then extend our analysis to capture multiple rounds of global updates, yielding a bound on the accumulated error in OTA-FL. We validate our theoretical results via extensive numerical simulations, which corroborate our derived analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20277
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Error Analysis for Over-the-Air Federated Learning under Misaligned and Time-Varying Channels
Ma, Xiaoyan
Zehtabi, Shahryar
Kim, Taejoon
Brinton, Christopher G.
Signal Processing
This paper investigates an OFDM-based over-the-air federated learning (OTA-FL) system, where multiple mobile devices, e.g., unmanned aerial vehicles (UAVs), transmit local machine learning (ML) models to a central parameter server (PS) for global model aggregation. The high mobility of local devices results in imperfect channel estimation, leading to a misalignment problem, i.e., the model parameters transmitted from different local devices do not arrive at the central PS simultaneously. Moreover, the mobility introduces time-varying uploading channels, which further complicates the aggregation process. All these factors collectively cause distortions in the OTA-FL training process which are underexplored. To quantify these effects, we first derive a closed-form expression for a single-round global model update in terms of these channel imperfections. We then extend our analysis to capture multiple rounds of global updates, yielding a bound on the accumulated error in OTA-FL. We validate our theoretical results via extensive numerical simulations, which corroborate our derived analysis.
title Error Analysis for Over-the-Air Federated Learning under Misaligned and Time-Varying Channels
topic Signal Processing
url https://arxiv.org/abs/2508.20277