FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting

Excerpt

arXiv:2608.14654v1 Announce Type: cross Abstract: Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy. A major challenge in FL is the non-Independent and Identically Distributed (non-IID) nature of data across devices, which hinders training efficiency and slows convergence. To tackle this, we propose Federated Impurity Weighting (FedImp), a novel algorithm that quantifies each device contribution based on