Federated Split Learning with Model Pruning and Gradient Quantization in Wireless Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Junhe, Ni, Wanli, Wang, Dongyu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910735733358592
author Zhang, Junhe
Ni, Wanli
Wang, Dongyu
author_facet Zhang, Junhe
Ni, Wanli
Wang, Dongyu
contents As a paradigm of distributed machine learning, federated learning typically requires all edge devices to train a complete model locally. However, with the increasing scale of artificial intelligence models, the limited resources on edge devices often become a bottleneck for efficient fine-tuning. To address this challenge, federated split learning (FedSL) implements collaborative training across the edge devices and the server through model splitting. In this paper, we propose a lightweight FedSL scheme, that further alleviates the training burden on resource-constrained edge devices by pruning the client-side model dynamicly and using quantized gradient updates to reduce computation overhead. Additionally, we apply random dropout to the activation values at the split layer to reduce communication overhead. We conduct theoretical analysis to quantify the convergence performance of the proposed scheme. Finally, simulation results verify the effectiveness and advantages of the proposed lightweight FedSL in wireless network environments.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06414
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Split Learning with Model Pruning and Gradient Quantization in Wireless Networks
Zhang, Junhe
Ni, Wanli
Wang, Dongyu
Machine Learning
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
As a paradigm of distributed machine learning, federated learning typically requires all edge devices to train a complete model locally. However, with the increasing scale of artificial intelligence models, the limited resources on edge devices often become a bottleneck for efficient fine-tuning. To address this challenge, federated split learning (FedSL) implements collaborative training across the edge devices and the server through model splitting. In this paper, we propose a lightweight FedSL scheme, that further alleviates the training burden on resource-constrained edge devices by pruning the client-side model dynamicly and using quantized gradient updates to reduce computation overhead. Additionally, we apply random dropout to the activation values at the split layer to reduce communication overhead. We conduct theoretical analysis to quantify the convergence performance of the proposed scheme. Finally, simulation results verify the effectiveness and advantages of the proposed lightweight FedSL in wireless network environments.
title Federated Split Learning with Model Pruning and Gradient Quantization in Wireless Networks
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
url https://arxiv.org/abs/2412.06414