A lightweight and personalized edge federated learning model

As a new distributed machine learning paradigm, federated learning has gained increasing attention in the industry and research community. However, federated learning is challenging to implement on edge devices with limited resources and heterogeneous data. This study aims to realize a lightweight a...

Full description

Saved in:
Bibliographic Details
Published in:Complex & intelligent systems 2024-06, Vol.10 (3), p.3577-3592
Main Authors: Yuan, Peiyan, Shi, Ling, Zhao, Xiaoyan, Zhang, Junna
Format: Article
Language:English
Subjects:
Accuracy
Alternating direction method of multipliers (ADMM)
Communication
Complexity
Computational Intelligence
Customization
Data heterogeneity
Data integrity
Data Structures and Information Theory
Edge computing
Energy consumption
Engineering
Federated learning
Intelligent systems
Lightweight
Lightweight model
Machine learning
Neural networks
Original Article
Personalized federated learning
Servers
Weight pruning
Weight reduction
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a new distributed machine learning paradigm, federated learning has gained increasing attention in the industry and research community. However, federated learning is challenging to implement on edge devices with limited resources and heterogeneous data. This study aims to realize a lightweight and personalized model through pruning and masking with insufficient resources and heterogeneous data. Particularly, the server first downloads the subnetwork to the client according to the mask, and client prunes the subnetwork with the alternating direction method of multipliers (ADMM), so as to remove the unimportant parameters and reduce the cost of training and communication. At the same time, mask is used to mark the pruning condition of the model. Then, the unpruned parts and masks of local models are transmitted to the server for aggregation. The experimental results showed that the accuracy of the proposed model was improved by 9.36%, and the communication cost was reduced by 1.45 times compared with state-of-the-art models. Last but not least, we deploy flower identification models in Android Studio to illustrate the practicality of the proposed method.
ISSN:2199-4536
2198-6053
DOI:10.1007/s40747-023-01332-9