학술논문
An Asynchronous Federated Learning Algorithm Based on a Backup Update of Model Version Parameters
Document Type
Conference
Author
Source
2023 3rd International Conference on Electrical Engineering and Control Science (IC2ECS) Electrical Engineering and Control Science (IC2ECS), 2023 3rd International Conference on. :1538-1544 Dec, 2023
Subject
Language
Abstract
Federated Learning (FL) is a practical approach to alleviate the problem of “Data Island” pain caused by privacy leakage in artificial intelligence (AI) security research. It enables multiple users to train a shared machine learning model cooperatively without uploading private data sets. However, in the process of FL model training, effectively coordinating the communication between participants and clients is the key to improving model training performance. The existing FL algorithms cannot balance model performance and accuracy stability. This paper proposes a novel FL algorithm based on a backup update of model version parameters (FedAvu). Adding a model version to help the server and client execute different training processes can improve the training efficiency and ensure the stability of the training accuracy. Experimental test results show that the proposed method can achieve better training efficiency on MNIST and CIFAR-10 data sets than existing algorithms.