@article{ART002899634},
author={Jung-Jun Kim and Jeon Seong Kang and Hyun-Joon Chung and Byung-Hoon Park},
title={Design of weighted federated learning framework based on local model validation},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2022},
volume={27},
number={11},
pages={13-18},
doi={10.9708/jksci.2022.27.11.013}

TY - JOUR
AU - Jung-Jun Kim
AU - Jeon Seong Kang
AU - Hyun-Joon Chung
AU - Byung-Hoon Park
TI - Design of weighted federated learning framework based on local model validation
JO - Journal of The Korea Society of Computer and Information
PY - 2022
VL - 27
IS - 11
PB - The Korean Society Of Computer And Information
SP - 13
EP - 18
SN - 1598-849X
AB - 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.
KW - AI;Federated Learning;Deep Learning;Mobile Computing;Object Classification
DO - 10.9708/jksci.2022.27.11.013
ER -

Jung-Jun Kim, Jeon Seong Kang, Hyun-Joon Chung and Byung-Hoon Park. (2022). Design of weighted federated learning framework based on local model validation. Journal of The Korea Society of Computer and Information, 27(11), 13-18.

Jung-Jun Kim, Jeon Seong Kang, Hyun-Joon Chung and Byung-Hoon Park. 2022, "Design of weighted federated learning framework based on local model validation", Journal of The Korea Society of Computer and Information, vol.27, no.11 pp.13-18. Available from: doi:10.9708/jksci.2022.27.11.013

Jung-Jun Kim, Jeon Seong Kang, Hyun-Joon Chung, Byung-Hoon Park "Design of weighted federated learning framework based on local model validation" Journal of The Korea Society of Computer and Information 27.11 pp.13-18 (2022) : 13.

Jung-Jun Kim, Jeon Seong Kang, Hyun-Joon Chung, Byung-Hoon Park. Design of weighted federated learning framework based on local model validation. 2022; 27(11), 13-18. Available from: doi:10.9708/jksci.2022.27.11.013

Jung-Jun Kim, Jeon Seong Kang, Hyun-Joon Chung and Byung-Hoon Park. "Design of weighted federated learning framework based on local model validation" Journal of The Korea Society of Computer and Information 27, no.11 (2022) : 13-18.doi: 10.9708/jksci.2022.27.11.013

Jung-Jun Kim; Jeon Seong Kang; Hyun-Joon Chung; Byung-Hoon Park. Design of weighted federated learning framework based on local model validation. Journal of The Korea Society of Computer and Information, 27(11), 13-18. doi: 10.9708/jksci.2022.27.11.013

Jung-Jun Kim; Jeon Seong Kang; Hyun-Joon Chung; Byung-Hoon Park. Design of weighted federated learning framework based on local model validation. Journal of The Korea Society of Computer and Information. 2022; 27(11) 13-18. doi: 10.9708/jksci.2022.27.11.013

Jung-Jun Kim, Jeon Seong Kang, Hyun-Joon Chung, Byung-Hoon Park. Design of weighted federated learning framework based on local model validation. 2022; 27(11), 13-18. Available from: doi:10.9708/jksci.2022.27.11.013

Jung-Jun Kim, Jeon Seong Kang, Hyun-Joon Chung and Byung-Hoon Park. "Design of weighted federated learning framework based on local model validation" Journal of The Korea Society of Computer and Information 27, no.11 (2022) : 13-18.doi: 10.9708/jksci.2022.27.11.013