Yurdem Betul, Kuzlu Murat, Gullu Mehmet Kemal, Catak Ferhat Ozgur, Tabassum Maliha
Department of Electrical and Electronics Engineering, Izmir Bakircay University, Izmir, Turkey.
Batten College of Engineering and Technology, Old Dominion University, Norfolk, VA, USA.
Heliyon. 2024 Sep 20;10(19):e38137. doi: 10.1016/j.heliyon.2024.e38137. eCollection 2024 Oct 15.
Federated learning (FL) is a distributed machine learning process, which allows multiple nodes to work together to train a shared model without exchanging raw data. It offers several key advantages, such as data privacy, security, efficiency, and scalability, by keeping data local and only exchanging model updates through the communication network. This review paper provides a comprehensive overview of federated learning, including its principles, strategies, applications, and tools along with opportunities, challenges, and future research directions. The findings of this paper emphasize that federated learning strategies can significantly help overcome privacy and confidentiality concerns, particularly for high-risk applications.
联邦学习（FL）是一种分布式机器学习过程，它允许多个节点协同工作以训练共享模型，而无需交换原始数据。通过将数据保持在本地，仅通过通信网络交换模型更新，它具有数据隐私、安全、高效和可扩展性等几个关键优势。这篇综述论文全面概述了联邦学习，包括其原理、策略、应用和工具，以及机遇、挑战和未来研究方向。本文的研究结果强调，联邦学习策略可以显著帮助克服隐私和保密问题，特别是对于高风险应用。
