Federated Learning
Optimization, privacy, and novelty areas of FL are the areas for further study in the field, as per the conclusion of the study.
Abstract
Federated Learning (FL) serves as one of the groundbreaking approaches in the present society, particularly in smart mobile applications, for designing a distributed environment for clients' model training without compromising data ownership. This paper narrows down the focus to how FL emerged, how it fits in distributed systems, and its usefulness in different fields. Research findings derived from thematic analysis include FL's contribution to improving the functionality of mobile applications and managing data privacy issues. Recommendations for the actual FL application underline such aspects as data management and protection. Optimization, privacy, and novelty areas of FL are the areas for further study in the field, as per the conclusion of the study.