Quantization-based chained privacy-preserving federated learning

Abstract Federated Learning (FL) is an advanced distributed machine learning framework crucial in protecting data privacy and security. By enabling multiple participants to train models while keeping their data local collaboratively, FL effectively mitigates the risks associated with centralized sto...

Full description

Saved in:
Bibliographic Details
Main Authors: Ya Liu, Shumin Wu, Yibo Li, Fengyu Zhao, Yanli Ren
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01420-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850273213235331072
author Ya Liu
Shumin Wu
Yibo Li
Fengyu Zhao
Yanli Ren
author_facet Ya Liu
Shumin Wu
Yibo Li
Fengyu Zhao
Yanli Ren
author_sort Ya Liu
collection DOAJ
description Abstract Federated Learning (FL) is an advanced distributed machine learning framework crucial in protecting data privacy and security. By enabling multiple participants to train models while keeping their data local collaboratively, FL effectively mitigates the risks associated with centralized storage and sharing of raw data. However, traditional FL schemes face significant challenges regarding communication efficiency, computational costs, and privacy preservation. For instance, its communication and computational overhead in edge computing scenarios is often excessively high, hindering real-time applications. This paper proposes an innovative federated learning framework, Q-Chain FL, integrating quantization compression techniques into a chained FL architecture. This Q-Chain FL scheme adopts efficient compression and transmission of model parameter differences at the user node and executes seamless decompression and aggregation at the server node. Experiments on several publicly available datasets, including MNIST, CIFAR-10, and CelebA, demonstrate low communication and computational overhead, fast convergence speed, and high security of Q-Chain FL. Compared to traditional FedAvg and Chain-PPFL, Q-Chain FL reduces communication overhead by approximately 62.5% and 44.7%, respectively. These results underscore the robustness and adaptability of Q-Chain FL in various datasets and real-world learning scenarios.
format Article
id doaj-art-b1bf0cdc783445a99b5aa05ae952a987
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-b1bf0cdc783445a99b5aa05ae952a9872025-08-20T01:51:35ZengNature PortfolioScientific Reports2045-23222025-05-0115111510.1038/s41598-025-01420-5Quantization-based chained privacy-preserving federated learningYa Liu0Shumin Wu1Yibo Li2Fengyu Zhao3Yanli Ren4The Department of Computer Science and Engineering, University of Shanghai for Science and TechnologyThe Department of Computer Science and Engineering, University of Shanghai for Science and TechnologyThe Department of Computer Science and Engineering, University of Shanghai for Science and TechnologyThe Department of Information and Intelligence Engineering, Shanghai Publishing and Printing CollegeThe School of Communication and Information Engineering, Shanghai UniversityAbstract Federated Learning (FL) is an advanced distributed machine learning framework crucial in protecting data privacy and security. By enabling multiple participants to train models while keeping their data local collaboratively, FL effectively mitigates the risks associated with centralized storage and sharing of raw data. However, traditional FL schemes face significant challenges regarding communication efficiency, computational costs, and privacy preservation. For instance, its communication and computational overhead in edge computing scenarios is often excessively high, hindering real-time applications. This paper proposes an innovative federated learning framework, Q-Chain FL, integrating quantization compression techniques into a chained FL architecture. This Q-Chain FL scheme adopts efficient compression and transmission of model parameter differences at the user node and executes seamless decompression and aggregation at the server node. Experiments on several publicly available datasets, including MNIST, CIFAR-10, and CelebA, demonstrate low communication and computational overhead, fast convergence speed, and high security of Q-Chain FL. Compared to traditional FedAvg and Chain-PPFL, Q-Chain FL reduces communication overhead by approximately 62.5% and 44.7%, respectively. These results underscore the robustness and adaptability of Q-Chain FL in various datasets and real-world learning scenarios.https://doi.org/10.1038/s41598-025-01420-5Federated learning (FL)QuantizationPrivacy-preservingLightweight
spellingShingle Ya Liu
Shumin Wu
Yibo Li
Fengyu Zhao
Yanli Ren
Quantization-based chained privacy-preserving federated learning
Scientific Reports
Federated learning (FL)
Quantization
Privacy-preserving
Lightweight
title Quantization-based chained privacy-preserving federated learning
title_full Quantization-based chained privacy-preserving federated learning
title_fullStr Quantization-based chained privacy-preserving federated learning
title_full_unstemmed Quantization-based chained privacy-preserving federated learning
title_short Quantization-based chained privacy-preserving federated learning
title_sort quantization based chained privacy preserving federated learning
topic Federated learning (FL)
Quantization
Privacy-preserving
Lightweight
url https://doi.org/10.1038/s41598-025-01420-5
work_keys_str_mv AT yaliu quantizationbasedchainedprivacypreservingfederatedlearning
AT shuminwu quantizationbasedchainedprivacypreservingfederatedlearning
AT yiboli quantizationbasedchainedprivacypreservingfederatedlearning
AT fengyuzhao quantizationbasedchainedprivacypreservingfederatedlearning
AT yanliren quantizationbasedchainedprivacypreservingfederatedlearning