Jifeng Chen

FedJigsaw: Multi-Agent Collaborative Model Reassembly for Decentralized Heterogeneous Federated Learning

FedJigsaw is proposed, a novel framework that reshapes model personalization as a dynamic and decentralized model assembly problem that outperforms state-of-the-art MHFL baselines by up to 13.8% in relative accuracy while significantly shrinking cross-client performance variance, but also slashes decision-making latency and peak memory footprint compared to existing policy-driven methods.