Skip to main content

Research Repository

Advanced Search

PFL-LDG: Privacy-preserving Federated Learning via Lightweight Device Grouping

Wang, Zhilu; Liu, Qi; Liu, Xiaodong

Authors

Zhilu Wang

Qi Liu



Abstract

The rapid growth of private data from distributed edge networks, driven by the proliferation of IoT sensors, wearable devices, and smartphones, offers significant opportunities for AI applications. However, traditional distributed machine learning methods struggle to address data privacy concerns effectively. Federated learning (FL) has appeared as a popular, innovative paradigm for distributed machine learning that enables collaborative training of models across multiple data silos while preserving privacy. Yet, in large-scale and complex edge networks, the convergence performance of existing FL methods deteriorates when dealing with highly heterogeneous data. This paper introduces PFL-LDG, a similarity-based lightweight privacy-protected grouping FL method that mitigates the impact of non-IID data on FL model performance in data-heterogeneous scenarios. Unlike conventional FL, PFL-LDG clusters devices based on data distribution similarity, reducing inefficiency and straggler issues while supplying personalized FL models for edge devices and enhancing FL accuracy. The paper’s main contribution is the proposal of a novel similarity-based lightweight privacy-protected grouping FL framework, focusing on improving privacy protection and training efficiency in heterogeneous edge resource-constrained FL systems.

Citation

Wang, Z., Liu, Q., & Liu, X. (2023, August). PFL-LDG: Privacy-preserving Federated Learning via Lightweight Device Grouping. Presented at The 9th IEEE International Conference on Privacy Computing and Data Security (PCDS 2023) as Part of the IEEE Smart World Congress 2023, Portsmouth, UK

Presentation Conference Type Conference Paper (published)
Conference Name The 9th IEEE International Conference on Privacy Computing and Data Security (PCDS 2023) as Part of the IEEE Smart World Congress 2023
Start Date Aug 28, 2023
End Date Aug 31, 2023
Acceptance Date May 19, 2023
Online Publication Date Mar 4, 2024
Publication Date 2023
Deposit Date Jun 9, 2023
Publicly Available Date Dec 31, 2023
Publisher Institute of Electrical and Electronics Engineers
Book Title 2023 IEEE Smart World Congress (SWC)
ISBN 9798350319811
DOI https://doi.org/10.1109/SWC57546.2023.10449141
Keywords Federated Learning, Non-IID, Personalization, Lightweight Encryption, Similarity-based Clustering, Privacy
Public URL http://researchrepository.napier.ac.uk/Output/3121186

Files

PFL-LDG: Privacy-preserving Federated Learning Via Lightweight Device Grouping (accetped version) (702 Kb)
PDF








You might also like



Downloadable Citations