FedFMC: Sequential Efficient Federated Learning on Non-iid Data

Over the past decade, improvements in machine learning accuracy has met rising consumer demand for use of learning models. Models were shown to be successful in a plethora of learning tasks, ranging from prediction-based recommendation to a variety of image processing tasks. Standard machine learning applications flourished in optimized processes where data would flow from user devices to centralized data centers for analysis. However, the rise of mobile and IoT (internet-of-things) devices has come with a changing dynamic resulting in new needs and constraints for machine learning. These include: (1) tighter restrictions [1] on usage of data in relation to user privacy, (2) demand for lower latency in many applications such as remote surgery, and (3) constraints of poor internet connectivity for accessibility in underdeveloped countries and offsite rigs (for research or oil exploration).