Gergely

A summary of dataset distribution techniques for Federated Learning on the CIFAR benchmark datasetFederated Learning (FL) is a method to train Machine Learning (ML) models in a distributed setting . The idea is that clients (for example hospitals) want to cooperate without sharing their private and sensitive data. Each client holds their private data in FL and trains an ML model on it. Then a central server collects and aggregates the model parameters, thus building a global model based on information from all the data…