Saved in:
Bibliographic Details
Main Authors: Zheng, Jingheng, Tian, Hui, Ni, Wanli, Tian, Yang, Zhang, Ping
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21893
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910032183951360
author Zheng, Jingheng
Tian, Hui
Ni, Wanli
Tian, Yang
Zhang, Ping
author_facet Zheng, Jingheng
Tian, Hui
Ni, Wanli
Tian, Yang
Zhang, Ping
contents In this paper, we propose a hybrid learning framework that combines federated and split learning, termed semi-federated learning (SemiFL), in which over-the-air computation is utilized for gradient aggregation. A key idea is to strategically adjust the learning rate by manipulating over-the-air distortion for improving SemiFL's convergence. Specifically, we intentionally amplify amplitude distortion to increase the learning rate in the non-stable region, thereby accelerating convergence and reducing communication energy consumption. In the stable region, we suppress noise perturbation to maintain a small learning rate for improving SemiFL's final convergence. Theoretical results demonstrate the antagonistic effects of over-the-air distortion in different regions, under both independent and identically distributed (IID) and non-IID data settings. Then, we formulate two energy consumption minimization problems, one for each region, which implements a two-region mean square error threshold configuration scheme. Accordingly, we propose two resource allocation algorithms with closed-form solutions. Simulation results show that under different network and data distribution conditions, strategically manipulating over-the-air distortion can efficiently adjust the learning rate to improve SemiFL's convergence. Moreover, energy consumption can be reduced by using the proposed algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21893
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Convergence for Semi-Federated Learning: An Energy-Efficient Approach by Manipulating Over-the-Air Distortion
Zheng, Jingheng
Tian, Hui
Ni, Wanli
Tian, Yang
Zhang, Ping
Signal Processing
In this paper, we propose a hybrid learning framework that combines federated and split learning, termed semi-federated learning (SemiFL), in which over-the-air computation is utilized for gradient aggregation. A key idea is to strategically adjust the learning rate by manipulating over-the-air distortion for improving SemiFL's convergence. Specifically, we intentionally amplify amplitude distortion to increase the learning rate in the non-stable region, thereby accelerating convergence and reducing communication energy consumption. In the stable region, we suppress noise perturbation to maintain a small learning rate for improving SemiFL's final convergence. Theoretical results demonstrate the antagonistic effects of over-the-air distortion in different regions, under both independent and identically distributed (IID) and non-IID data settings. Then, we formulate two energy consumption minimization problems, one for each region, which implements a two-region mean square error threshold configuration scheme. Accordingly, we propose two resource allocation algorithms with closed-form solutions. Simulation results show that under different network and data distribution conditions, strategically manipulating over-the-air distortion can efficiently adjust the learning rate to improve SemiFL's convergence. Moreover, energy consumption can be reduced by using the proposed algorithms.
title Improving Convergence for Semi-Federated Learning: An Energy-Efficient Approach by Manipulating Over-the-Air Distortion
topic Signal Processing
url https://arxiv.org/abs/2506.21893