Research Advanced in Federated Learning

Ruixin Gao

2024

Abstract

As an emerging machine learning framework, federated learning has received extensive attention in recent years and has been applied to various fields, such as financial, medical, intelligent city, and automatic driving. Different from the traditional centralized machine learning methods, federated learning algorithms allow the model trained locally to update the center server, greatly protecting user privacy and data security. Through extensive literature research and analysis, this paper aims to report on the latest research progress of federated learning. According to the organizational difference in training data distribution, this paper introduces the representative federated learning studies from the aspects of horizontal federated learning, vertical federated learning and transferred federated learning, including their design ideas and basic pipelines. In addition, a discussion about the existing issues and future development directions are given, especially how to reduce the impact of the central server once the subservers are attacked. This is supposed to bring some new insight to the federated learning community.

Paper Citation

in Harvard Style

Gao R. (2024). Research Advanced in Federated Learning. In Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI; ISBN 978-989-758-713-9, SciTePress, pages 574-579. DOI: 10.5220/0012959500004508

in Bibtex Style

@conference{emiti24,
author={Ruixin Gao},
title={Research Advanced in Federated Learning},
booktitle={Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI},
year={2024},
pages={574-579},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012959500004508},
isbn={978-989-758-713-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI
TI - Research Advanced in Federated Learning
SN - 978-989-758-713-9
AU - Gao R.
PY - 2024
SP - 574
EP - 579
DO - 10.5220/0012959500004508
PB - SciTePress