Edge Federated Optimization for Heterogeneous Data

Hsin-Tung Lin and Chih-Yu Wen ()
Additional contact information
Hsin-Tung Lin: Department of Electrical Engineering, National Chung Hsing University, Taichung 40227, Taiwan
Chih-Yu Wen: Department of Electrical Engineering, National Chung Hsing University, Taichung 40227, Taiwan

Future Internet, 2024, vol. 16, issue 4, 1-23

Abstract: This study focuses on optimizing federated learning in heterogeneous data environments. We implement the FedProx and a baseline algorithm (i.e., the FedAvg) with advanced optimization strategies to tackle non-IID data issues in distributed learning. Model freezing and pruning techniques are explored to showcase the effective operations of deep learning models on resource-constrained edge devices. Experimental results show that at a pruning rate of 10%, the FedProx with structured pruning in the MIT-BIH and ST databases achieved the best F1 scores, reaching 96.01% and 77.81%, respectively, which achieves a good balance between system efficiency and model accuracy compared to those of the FedProx with the original configuration, reaching F1 scores of 66.12% and 89.90%, respectively. Similarly, with layer freezing technique, unstructured pruning method, and a pruning rate of 20%, the FedAvg algorithm effectively balances classification performance and degradation of pruned model accuracy, achieving F1 scores of 88.75% and 72.75%, respectively, compared to those of the FedAvg with the original configuration, reaching 56.82% and 85.80%, respectively. By adopting model optimization strategies, a practical solution is developed for deploying complex models in edge federated learning, vital for its efficient implementation.

Keywords: federated learning; deep learning; embedded systems; heterogeneous; pruning (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/4/142/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/4/142/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:16:y:2024:i:4:p:142-:d:1380113

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().