Abstract
Federated learning (FL) is a cutting-edge machine learning platform that protects user privacy while enabling collaborative learning across various devices. It is particularly relevant in the current environment when massive volumes of data are generated at the edge of networks by developing technologies like social networking, cloud computing, edge computing, and the Internet of Things. FL reduces the possibility of unauthorized access by third parties by allowing data to stay on local devices, hence mitigating any privacy breaches. The integration of FL in Cloud, Edge, and hybrid Edge-Cloud settings are some of the computing paradigms that this study investigates. We highlight the salient features of FL, go over the main obstacles to its implementation and use, and make recommendations for future study directions. Furthermore, we assess how FL, by facilitating safe and cooperative data sharing among vehicles, can improve service quality in the Internet of Vehicles (IoV). Our study findings are intended to offer practical insights and suggestions that may have an impact on a variety of computing technology research topics.
