Improving Federated Learning Efficiency with PruneFL: A Healthcare Perspective

In healthcare, accessing diverse and large datasets for machine learning poses challenges due to data privacy concerns. Federated learning (FL) addresses this by training models on decentralized data while preserving privacy. We propose PruneFL, a FL paradigm that leverages model pruning to reduce complexity and enhance efficiency. PruneFL strikes a balance between model accuracy and efficiency by reducing parameters, accelerating convergence, and minimizing communication overhead. Our approach addresses critical FL challenges and demonstrates efficacy in resource-constrained environments like healthcare.