Meta-Learning for Adaptive Model Selection in Federated Learning

Abstract

Federated Learning (FL) has emerged as a promising approach for training machine learning models across decentralized devices while preserving data privacy. However, a significant limitation of traditional FL is the static nature of model selection. Typically, all clients are trained with the same base model, regardless of the heterogeneity in their local data distributions. This static approach often leads to suboptimal performance, particularly in scenarios with diverse client datasets. This paper proposes a novel meta-learning framework to address this limitation. The framework learns a central model that dynamically selects the most appropriate base model for each client based on its local data characteristics. This adaptive model selection process aims to improve the overall system performance and efficiency of federated learning. The key contributions are the introduction of adaptability into the model selection stage and the development of a meta-learning approach for achieving this adaptation.