본문 바로가기
  • Home

Design of weighted federated learning framework based on local model validation

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2022, 27(11), pp.13-18
  • DOI : 10.9708/jksci.2022.27.11.013
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : September 6, 2022
  • Accepted : October 26, 2022
  • Published : November 30, 2022

Jungjun Kim 1 Jeon-Sung Kang 1 Hyun-Joon Chung 1 Byung-Hoon Park 2

1한국로봇융합연구원
2티쓰리큐 주식회사

Accredited

ABSTRACT

In this paper, we proposed VW-FedAVG(Validation based Weighted FedAVG) which updates the global model by weighting according to performance verification from the models of each device participating in the training. The first method is designed to validate each local client model through validation dataset before updating the global model with a server side validation structure. The second is a client-side validation structure, which is designed in such a way that the validation data set is evenly distributed to each client and the global model is after validation. MNIST, CIFAR-10 is used, and the IID, Non-IID distribution for image classification obtained higher accuracy than previous studies.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.