Aggregation Methods Based on Quality Model Assessment for Federated Learning Applications: Overview and Comparative Analysis

Abstract

Federated learning (FL) offers the possibility of collaboration between multiple devices while maintaining data confidentiality, as required by the General Data Protection Regulation (GDPR). Though FL can keep local data private, it may encounter problems when dealing with non-independent and identically distributed data (non-IID), insufficient local training samples or cyber-attacks. This paper introduces algorithms that can provide a reliable aggregation of the global model by investigating the accuracy of models received from clients. This allows reducing the influence of less confident nodes, who were potentially attacked or unable to perform successful training. The analysis includes the proposed FedAcc and FedAccSize algorithms, together with their new extension based on the Lasso regression, FedLasso. FedAcc and FedAccSize set the confidence in each client based only on local models’ accuracy, while FedLasso exploits additional details related to predictions, like predicted class probabilities, to support a refined aggregation. The ability of the proposed algorithms to protect against intruders or underperforming clients is demonstrated experimentally using testing scenarios involving independent and identically distributed (IID) data as well as non-IID data. The comparison with the established FedAvg and FedAvgM algorithms shows that exploiting the quality of the client models is essential for reliable aggregation, which enables rapid and robust improvement in the global model.