• Journal of Internet Computing and Services
    ISSN 2287 - 1136 (Online) / ISSN 1598 - 0170 (Print)
    https://jics.or.kr/
Menu

Efficient distributed consensus optimization based on patterns and groups for federated learning


Seung Ju Kang, Ji Young Chun, Geontae Noh, Ik Rae Jeong, Journal of Internet Computing and Services, Vol. 23, No. 4, pp. 73-85, Aug. 2022
10.7472/jksii.2022.23.4.73, Full Text:  HTML
Keywords: Federated learning, Optimization, Weight model, Communication time, Privacy, ADMM

Abstract

In the era of the 4th industrial revolution, where automation and connectivity are maximized with artificial intelligence, the importance of data collection and utilization for model update is increasing. In order to create a model using artificial intelligence technology, it is usually necessary to gather data in one place so that it can be updated, but this can infringe users' privacy. In this paper, we introduce federated learning, a distributed machine learning method that can update models in cooperation without directly sharing distributed stored data, and introduce a study to optimize distributed consensus among participants without an existing server. In addition, we propose a pattern and group-based distributed consensus optimization algorithm that uses an algorithm for generating patterns and groups based on the Kirkman Triple System, and performs parallel updates and communication. This algorithm guarantees more privacy than the existing distributed consensus optimization algorithm and reduces the communication time until the model converges.


Statistics
Show / Hide Statistics

Statistics (Past 3 Years)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[APA Style]
Kang, S., Chun, J., Noh, G., & Jeong, I. (2022). Efficient distributed consensus optimization based on patterns and groups for federated learning. Journal of Internet Computing and Services, 23(4), 73-85. DOI: 10.7472/jksii.2022.23.4.73.

[IEEE Style]
S. J. Kang, J. Y. Chun, G. Noh, I. R. Jeong, "Efficient distributed consensus optimization based on patterns and groups for federated learning," Journal of Internet Computing and Services, vol. 23, no. 4, pp. 73-85, 2022. DOI: 10.7472/jksii.2022.23.4.73.

[ACM Style]
Seung Ju Kang, Ji Young Chun, Geontae Noh, and Ik Rae Jeong. 2022. Efficient distributed consensus optimization based on patterns and groups for federated learning. Journal of Internet Computing and Services, 23, 4, (2022), 73-85. DOI: 10.7472/jksii.2022.23.4.73.