Communication-Efficient Federated Learning via Clipped Uniform Quantization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bozorgasl, Zavareh, Chen, Hao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909427727073280
author Bozorgasl, Zavareh
Chen, Hao
author_facet Bozorgasl, Zavareh
Chen, Hao
contents This paper presents a novel approach to enhance communication efficiency in federated learning through clipped uniform quantization. By leveraging optimal clipping thresholds and client-specific adaptive quantization schemes, the proposed method significantly reduces bandwidth and memory requirements for model weight transmission between clients and the server while maintaining competitive accuracy. We investigate the effects of symmetric clipping and uniform quantization on model performance, emphasizing the role of stochastic quantization in mitigating artifacts and improving robustness. Extensive simulations demonstrate that the method achieves near-full-precision performance with substantial communication savings. Moreover, the proposed approach facilitates efficient weight averaging based on the inverse of the mean squared quantization errors, effectively balancing the trade-off between communication efficiency and model accuracy. Moreover, in contrast to federated averaging, this design obviates the need to disclose client-specific data volumes to the server, thereby enhancing client privacy. Comparative analysis with conventional quantization methods further confirms the efficacy of the proposed scheme.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13365
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Communication-Efficient Federated Learning via Clipped Uniform Quantization
Bozorgasl, Zavareh
Chen, Hao
Machine Learning
Multiagent Systems
Signal Processing
This paper presents a novel approach to enhance communication efficiency in federated learning through clipped uniform quantization. By leveraging optimal clipping thresholds and client-specific adaptive quantization schemes, the proposed method significantly reduces bandwidth and memory requirements for model weight transmission between clients and the server while maintaining competitive accuracy. We investigate the effects of symmetric clipping and uniform quantization on model performance, emphasizing the role of stochastic quantization in mitigating artifacts and improving robustness. Extensive simulations demonstrate that the method achieves near-full-precision performance with substantial communication savings. Moreover, the proposed approach facilitates efficient weight averaging based on the inverse of the mean squared quantization errors, effectively balancing the trade-off between communication efficiency and model accuracy. Moreover, in contrast to federated averaging, this design obviates the need to disclose client-specific data volumes to the server, thereby enhancing client privacy. Comparative analysis with conventional quantization methods further confirms the efficacy of the proposed scheme.
title Communication-Efficient Federated Learning via Clipped Uniform Quantization
topic Machine Learning
Multiagent Systems
Signal Processing
url https://arxiv.org/abs/2405.13365