Performance Enhancement of Federated Learning through Effective Client Management 


Vol. 13,  No. 12, pp. 661-668, Dec.  2024
https://doi.org/10.3745/TKIPS.2024.13.12.661


PDF
  Abstract

In a federated learning with non-IID datasets, training delays and poor performance due to unequalness in datasets among clients are prevalent. To prevent such performance degradation, selecting appropriate clients is a crucial part of training. This paper applies a UCB algorithm based on a virtual queue for client selection in federated learning models. Unlike the traditional UCB algorithm, the proposed client selection method reflects the training progress of federated learning. It can reduce the proposed model’s training time. Additionally, to further improve the performance of the model, the exploration of clients through UCB is dynamically adjusted. Once the training is stabilized in the mid-phase, the client exploration is involved to extract additional performance gain. The experimental results demonstrate the benefit of this algorithm such as a reduced training time and an improved model accuracy

  Statistics
  Cite this article

[IEEE Style]

K. T. Woo and K. Taejoon, "Performance Enhancement of Federated Learning through Effective Client Management," The Transactions of the Korea Information Processing Society, vol. 13, no. 12, pp. 661-668, 2024. DOI: https://doi.org/10.3745/TKIPS.2024.13.12.661.

[ACM Style]

Kang Tae Woo and Kim Taejoon. 2024. Performance Enhancement of Federated Learning through Effective Client Management. The Transactions of the Korea Information Processing Society, 13, 12, (2024), 661-668. DOI: https://doi.org/10.3745/TKIPS.2024.13.12.661.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals