Research on the Application of FedDyn Algorithm in Federated Learning Based on Taylor

Zijia Li

2025

Abstract

With the rise of distributed machine learning, Federated Learning (FL), as a distributed machine learning framework, can realize multi-party collaborative modelling under the premise of protecting data privacy. However, traditional federated learning algorithms often face problems such as slow model convergence speed and low accuracy in non-independent identically distributed (Non-IID) data scenarios. In this paper, a Federated Learning with Dynamic Regularization (FedDyn) algorithm based on Taylor expansion is proposed, which aims to improve the performance of federated learning through dynamic regularization technology. As a dynamic regularization method, it can dynamically adjust the direction of each round of updates during model training. In this paper, the dynamic adjustment mechanism of the FedDyn algorithm is improved through the optimization method based on Taylor expansion, to improve the convergence speed and accuracy of generated learning in heterogeneous data and unbalanced environments. Experimental results show that the FedDyn algorithm based on Taylor deployment has significant improvement in convergence speed and model accuracy, especially in highly heterogeneous data environments, which is significantly better than traditional federated learning algorithms and has good generalization performance.

Paper Citation

in Harvard Style

Li Z. (2025). Research on the Application of FedDyn Algorithm in Federated Learning Based on Taylor. In Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-765-8, SciTePress, pages 123-127. DOI: 10.5220/0013679700004670

in Bibtex Style

@conference{icdse25,
author={Zijia Li},
title={Research on the Application of FedDyn Algorithm in Federated Learning Based on Taylor},
booktitle={Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2025},
pages={123-127},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013679700004670},
isbn={978-989-758-765-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Research on the Application of FedDyn Algorithm in Federated Learning Based on Taylor
SN - 978-989-758-765-8
AU - Li Z.
PY - 2025
SP - 123
EP - 127
DO - 10.5220/0013679700004670
PB - SciTePress