Federated Learning Algorithms: Towards Next Generation Communication Systems
Konstantinos D. Stergiou, Kostas E. Psannis · 2020
We provide a survey of four different categories of Federated Learning algorithms and their limitations as these were unveiled through experiments using commonly accepted data sets. The level of data heterogeneity forms a potential benchmark to compare Federated Averaging, Gradient Descent, Evolutionary, and Differential Privacy methods and, among other criteria, identifies the gaps that need to be addressed from future approaches.