Literature Review of Federated Learning in Various Applications, ‎Challenges, and Emerging Research Directions

Main Article Content

Tiba Saad Mohammed
Hilal Al-Libawy

Abstract

Federated Learning (FL) is an emerging technology recently used collaboratively with machine learning approaches. It has been the key to an effective solution to the major global problem of protecting sensitive data. The data is trained locally within the clients, the server collects the models trained from the clients and the global model is generated. They have been used in many applications, particularly in applications that require data protection, such as medical applications whose data is legally protected. This paper discusses standardized learning applications that are still in their infancy due to the many challenges facing researchers. The latest developments in Federated Learning and open fields are outlined for researchers to develop this technology. It has been concluded that the most critical area researchers seek to develop is improving the global model. The main causes and challenges affecting the quality of global models were clarified. Finally, some proposals are presented to improve the Federated Learning technology.

Downloads

Download data is not yet available.

Article Details

How to Cite
[1]
“Literature Review of Federated Learning in Various Applications, ‎Challenges, and Emerging Research Directions”, JUBES, vol. 32, no. 2, pp. 189–204, Apr. 2024, doi: 10.29196/j7gh8c05.
Section
Articles

How to Cite

[1]
“Literature Review of Federated Learning in Various Applications, ‎Challenges, and Emerging Research Directions”, JUBES, vol. 32, no. 2, pp. 189–204, Apr. 2024, doi: 10.29196/j7gh8c05.

Similar Articles

You may also start an advanced similarity search for this article.