Improve model-contrastive federated learning by momentum contrast

Xiaoyang Chen; Bokang Li; Weiheng Li

doi:10.1117/12.2675419

25 May 2023 Improve model-contrastive federated learning by momentum contrast

Xiaoyang Chen, Bokang Li, Weiheng Li

Proceedings Volume 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022); 126360U (2023) https://doi.org/10.1117/12.2675419
Event: Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 2022, Shenyang, China

Abstract

FedAvg is a classic algorithm for Federated Learning. The MOON algorithm is based on the idea of comparative learning. The model in the previous round is a negative sample, and the global model is a positive sample, which improves the local training of FedAvg. However, in the study of MOON, it was found that since the MOON algorithm compares models rather than pictures, the number of negative samples is difficult to expand, and in traditional comparative learning, the total number of negative samples will significantly affect the effect of comparative learning, when the model in this round is far from the model in the previous round, it may approach the earlier model, thus reducing the efficiency of contrastive learning. So, this paper studied more algorithms related to contrastive learning and federated learning. Finally, a dictionary was built based on the MoCo algorithm to save the previously generated local models. The improved MOON algorithm was named FedCOMO. With the extension of negative samples, the training accuracy on the CIFAR-10 dataset can exceed MOON.

Citation Download Citation

Xiaoyang Chen, Bokang Li, and Weiheng Li "Improve model-contrastive federated learning by momentum contrast", Proc. SPIE 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 126360U (25 May 2023); https://doi.org/10.1117/12.2675419

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available