ChainLearn: A Blockchain-Based Capacity-Aware Framework for Federated Ensemble Learning
Researchers have developed ChainLearn, a new framework for federated ensemble learning that addresses the challenge of varying computational capacities among participating institutions. This system uses blockchain technology to manage policies and store metrics, while off-chain learning and weighted ensemble methods adapt to different hospital hardware. Experiments show ChainLearn achieves competitive accuracy with significantly reduced communication overhead compared to traditional federated learning approaches. AI
IMPACT Introduces a novel approach to federated learning that enhances efficiency and participation for institutions with diverse computational resources.