Update Estimation and Scheduling for Over-the-Air Federated Learning with Energy Harvesting Devices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bagci, Furkan, Tegin, Busra, Kazemi, Mohammad, Duman, Tolga M.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909898830249984
author Bagci, Furkan
Tegin, Busra
Kazemi, Mohammad
Duman, Tolga M.
author_facet Bagci, Furkan
Tegin, Busra
Kazemi, Mohammad
Duman, Tolga M.
contents We study over-the-air (OTA) federated learning (FL) for energy harvesting devices with heterogeneous data distribution over wireless fading multiple access channel (MAC). To address the impact of low energy arrivals and data heterogeneity on global learning, we propose user scheduling strategies. Specifically, we develop two approaches: 1) entropy-based scheduling for known data distributions and 2) least-squares-based user representation estimation for scheduling with unknown data distributions at the parameter server. Both methods aim to select diverse users, mitigating bias and enhancing convergence. Numerical and analytical results demonstrate improved learning performance by reducing redundancy and conserving energy.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18298
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Update Estimation and Scheduling for Over-the-Air Federated Learning with Energy Harvesting Devices
Bagci, Furkan
Tegin, Busra
Kazemi, Mohammad
Duman, Tolga M.
Machine Learning
Distributed, Parallel, and Cluster Computing
We study over-the-air (OTA) federated learning (FL) for energy harvesting devices with heterogeneous data distribution over wireless fading multiple access channel (MAC). To address the impact of low energy arrivals and data heterogeneity on global learning, we propose user scheduling strategies. Specifically, we develop two approaches: 1) entropy-based scheduling for known data distributions and 2) least-squares-based user representation estimation for scheduling with unknown data distributions at the parameter server. Both methods aim to select diverse users, mitigating bias and enhancing convergence. Numerical and analytical results demonstrate improved learning performance by reducing redundancy and conserving energy.
title Update Estimation and Scheduling for Over-the-Air Federated Learning with Energy Harvesting Devices
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2501.18298