Model Splitting Enhanced Communication-Efficient Federated Learning for CSI Feedback

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dong, Yanjie, Zhang, Haijun, Chen, Gaojie, Fan, Xiaoyi, Leung, Victor C. M., Hu, Xiping
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909637106728960
author Dong, Yanjie
Zhang, Haijun
Chen, Gaojie
Fan, Xiaoyi
Leung, Victor C. M.
Hu, Xiping
author_facet Dong, Yanjie
Zhang, Haijun
Chen, Gaojie
Fan, Xiaoyi
Leung, Victor C. M.
Hu, Xiping
contents Recent advancements have introduced federated machine learning-based channel state information (CSI) compression before the user equipments (UEs) upload the downlink CSI to the base transceiver station (BTS). However, most existing algorithms impose a high communication overhead due to frequent parameter exchanges between UEs and BTS. In this work, we propose a model splitting approach with a shared model at the BTS and multiple local models at the UEs to reduce communication overhead. Moreover, we implant a pipeline module at the BTS to reduce training time. By limiting exchanges of boundary parameters during forward and backward passes, our algorithm can significantly reduce the exchanged parameters over the benchmarks during federated CSI feedback training.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Model Splitting Enhanced Communication-Efficient Federated Learning for CSI Feedback
Dong, Yanjie
Zhang, Haijun
Chen, Gaojie
Fan, Xiaoyi
Leung, Victor C. M.
Hu, Xiping
Signal Processing
Recent advancements have introduced federated machine learning-based channel state information (CSI) compression before the user equipments (UEs) upload the downlink CSI to the base transceiver station (BTS). However, most existing algorithms impose a high communication overhead due to frequent parameter exchanges between UEs and BTS. In this work, we propose a model splitting approach with a shared model at the BTS and multiple local models at the UEs to reduce communication overhead. Moreover, we implant a pipeline module at the BTS to reduce training time. By limiting exchanges of boundary parameters during forward and backward passes, our algorithm can significantly reduce the exchanged parameters over the benchmarks during federated CSI feedback training.
title Model Splitting Enhanced Communication-Efficient Federated Learning for CSI Feedback
topic Signal Processing
url https://arxiv.org/abs/2506.04113