Federated learning (FL) is a new technology that has been a hot research topic. It enables the training of an algorithm across multiple decentralized edge devices or servers holding local data samples without exchanging them. Federated Learning embodies the principles of focused minimization and data collection, costs and can reducing privacy risks, and centralized machine learning approaches. Motivated by the growth in Federated Learning research, this thesis considers advances and presents many collections of challenges and open problems. This monograph describes the defining characteristics and challenges of the Federated Learning setting, highlights important practical considerations, constraints, and then enumerates a range of valuable research directions. The goals of this work are to highlight research problems that are of significant theoretical and practical interest, and to encourage research on problems that could have significant real-world impact. Finally, the paper highlights the limitations present in recent works and presents some future directions for this technology.

Federated Learning, Decentralized Machine Learning, Smart Health Care.