FairDPFL-SCS: Fair Dynamic Personalized Federated Learning with strategic client selection for improved accuracy and fairness

Sabah, Fahad ORCID: https://orcid.org/0000-0003-1558-2616, Chen, Yuwen, Yang, Zhen, Raheem, Abdul, Azam, Muhammad, Ahmad, Nadeem and Sarwar, Raheem ORCID: https://orcid.org/0000-0002-0640-807X (2024) FairDPFL-SCS: Fair Dynamic Personalized Federated Learning with strategic client selection for improved accuracy and fairness. Information Fusion, 115. 102756. ISSN 1566-2535

Preview

Accepted Version Available under License Creative Commons Attribution. Download (12MB) | Preview

Abstract

Personalized federated learning (PFL) addresses the significant challenge of non-independent and identically distributed (non-IID) data across clients in federated learning (FL). Our proposed framework, “FairDPFL-SCS: Fair Dynamic Personalized Federated Learning with Strategic Client Selection”, marks a notable advancement in this domain. By integrating dynamic learning rate adjustments and a strategic client selection mechanism, our approach effectively mitigates the challenges posed by non-IID data while enhancing model personalization, fairness, and efficiency. We evaluated FairDPFL-SCS using standard datasets, including MNIST, FashionMNIST, and SVHN, employing architectures like VGG and CNN. Our model achieved impressive results, attaining 99.04% accuracy on MNIST, 89.19% on FashionMNIST, and 90.9% on SVHN. These results represent a substantial improvement over existing methods, including a highest increase of 16.74% in accuracy on SVHN when compared to the best-performing benchmark methods. In particular, our method also demonstrated lower fairness variance, presenting the importance of fairness in model personalization, a frequently overlooked aspect in FL research. Through extensive experiments, we validate the superior performance of FairDPFL-SCS compared to benchmark PFL approaches, highlighting significant improvements over state-of-the-art methods. This work represents a promising step forward in the field of federated learning, offering a comprehensive solution to the challenges presented by non-IID data while prioritizing fairness and efficiency in model personalization.