Skip to main content

Research Repository

Advanced Search

GSFL: A Privacy-Preserving Grouping-Split Federated Learning Approach in Resource-Constrained Edge Computing Scenarios

Liu, Qi; Wang, Zhilu; Zhou, Xiaokang; Zhang, Yonghong; Liu, Xiaodong; Lin, Haiyang

Authors

Qi Liu

Zhilu Wang

Xiaokang Zhou

Yonghong Zhang

Haiyang Lin



Abstract

The advancement of mobile multimedia communications, 5G, and Internet of Things (IoT) has led to the widespread use of edge devices, including sensors, smartphones, and wearables. This has generated in a large amount of distributed data, leading to new prospects for deep learning. However, this data is confined within data silos and contains sensitive information, making it difficult to be processed in a centralized manner, particularly under stringent data privacy regulations. Federated learning (FL) offers a solution by enabling collaborative learning while ensuring privacy. Nonetheless, data and device heterogeneity complicate FL implementation. This research presents a specialized FL algorithm for heterogeneous edge computing. It integrates a lightweight grouping strategy for homogeneous devices, a scheduling algorithm within groups, and a Split Learning (SL) approach. These contributions enhance model accuracy and training speed, alleviate the burden on resource-constrained devices, and strengthen privacy. Experimental results demonstrate that the GSFL outperforms FedAvg and SplitFed by 6.53× and 1.18×. Under experimental conditions with 𝛼 = 0.05, representing a highly heterogeneous data distribution typical of extreme Non-IID scenarios, GSFL showed better accuracy compared to FedAvg by 10.64%, HACCS by 4.53%, and Cluster-HSFL by 1.16%. GSFL effectively balances privacy protection and computational efficiency for real-world applications in mobile multimedia communications.

Citation

Liu, Q., Wang, Z., Zhou, X., Zhang, Y., Liu, X., & Lin, H. (online). GSFL: A Privacy-Preserving Grouping-Split Federated Learning Approach in Resource-Constrained Edge Computing Scenarios. ACM transactions on autonomous and adaptive systems, https://doi.org/10.1145/3725221

Journal Article Type Article
Acceptance Date Mar 15, 2025
Online Publication Date Mar 20, 2025
Deposit Date Mar 18, 2025
Publicly Available Date Mar 20, 2025
Journal ACM Transactions on Autonomous and Adaptive Systems
Print ISSN 1556-4665
Electronic ISSN 1556-4703
Publisher Association for Computing Machinery (ACM)
Peer Reviewed Peer Reviewed
DOI https://doi.org/10.1145/3725221
Keywords Federated learning, Split learning, Non-IID, Clustering
Public URL http://researchrepository.napier.ac.uk/Output/4177687
This output contributes to the following UN Sustainable Development Goals:

SDG 9 - Industry, Innovation and Infrastructure

Build resilient infrastructure, promote inclusive and sustainable industrialisation and foster innovation

Files

GSFL: A Privacy-preserving Grouping-Split Federated Learning Approach in Resource-constrained Edge Computing Scenarios (accepted version) (5.8 Mb)
PDF








You might also like



Downloadable Citations