Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning

arXiv:2405.04122v1 Announce Type: new
Abstract: Federated Learning (FL) enables multiple devices to collaboratively train a shared model while ensuring data privacy. The selection of participating devices in each training round critically affects both the model performance and training efficiency, especially given the vast heterogeneity in training capabilities and data distribution across devices. To address these challenges, we introduce a novel device selection solution called FedRank, which is an end-to-end, ranking-based approach that is pre-trained by imitation learning against state-of-the-art analytical …

abstract arxiv capabilities client cs.dc cs.lg data data privacy devices distribution efficiency federated learning imitation learning multiple performance privacy ranking train training type vast while