Comparative Federated Algorithms for Solving Non- IID Data Challenges
Comparative Federated Algorithms for Solving Non- IID Data Challenges
Abstract
This study evaluates three Federated Learning (FL) algorithms—FedAvg, Federated Proximal (FedProx), and MOON—by assessing their performance in Independent and Identically Distributed (IID) and non-IID settings. We found that FedAvg performs best in IID scenarios, offering quick convergence and high accuracy. However, MOON stood out as the top performer in non-IID settings, thanks to its contrastive learning method, providing better stability and accuracy across heterogeneous data. FedProx improved over FedAvg in handling non-IID data but was less effective than MOON. Our findings suggest that for environments with IID data, FedAvg is ideal, while MOON is more suitable for non-IID cases. We also highlight the need for further research into personalized FL, regularization techniques, and multimodal data integration.
Acknowledgments
Null