Analysis on Optimizing Federated Proximal Algorithm for Heterogeneous and Secure Collaborative Learning

Federated Learning (FL) has to decentralize the model training but maintains users data privacy, hence it is potentially essential in critical applications such as healthcare, finance, etc. For FL, the main obstacles remain the client heterogeneity and the sensitivity to any security attacks, which severely hinder its application to real scenarios. In this paper, the thesis studies the edge cases of the Federated Proximal (FedProx) algorithm that incur this phenomenon and suggests six ways for mitigating them. More precisely, the thesis considers adaptive regularization, knowledge distillation and transfer, optimization on efficiency, security defenses, client selection strategies, and approaches dealing with behavioural heterogeneity. Experiments conducted on benchmark datasets such as Canadian Institute for Advanced Research (CIFAR)-10 and Federated Extended Modified National Institute of Standards and Technology (FEMNIST) demonstrate that these strategies can improve FedProx accuracy by up to 7.2% and reduce communication rounds by up to 30%. The thesiss findings enhance the robustness, scalability, and personalization of FedProx in heterogeneous and adversarial settings. Such enhancements have a practical benefit for implementing FL systems over various real-world settings.