FedOS: using open-set learning to stabilize training in federated learning

TL;DR

FedOS introduces an open-set learning approach to address training stability issues in federated learning, enhancing model robustness across diverse client data distributions.

Contribution

The paper proposes a novel open-set learning method for federated learning, improving training stability and model performance in heterogeneous data environments.

Findings

Open-set learning improves federated training stability

The proposed method outperforms existing approaches in heterogeneous settings

Experimental results demonstrate enhanced model robustness

Abstract

Federated Learning is a recent approach to train statistical models on distributed datasets without violating privacy constraints. The data locality principle is preserved by sharing the model instead of the data between clients and the server. This brings many advantages but also poses new challenges. In this report, we explore this new research area and perform several experiments to deepen our understanding of what these challenges are and how different problem settings affect the performance of the final model. Finally, we present a novel approach to one of these challenges and compare it to other methods found in literature.