<ul><li>Federated learning is a decentralized learning architecture that consumes a lot of network transmission resources.</li><li>A new adaptive clustering scheme is proposed to reduce communication costs in federated learning.</li><li>The scheme dynamically adjusts the number of clusters to find the most ideal grouping results.</li><li>Experimental results show a reduction of communication and transmission costs by almost 50% without affecting model accuracy.</li></ul>

An Adaptive Clustering Scheme for Client Selections in Communication-Efficient Federated Learning

Discover more