<ul><li>Federated Learning (FL) allows training a shared machine learning model while keeping data local to clients.</li><li>The widely used FedAvg algorithm shows a decrease in learning accuracy as the number of clients increases.</li><li>To address this issue, a method called Knowledgeable Client Insertion (KCI) is proposed, which introduces a small number of knowledgeable clients with large sets of data samples.</li><li>The KCI approach improves the learning accuracy of FL even with the normal FedAvg aggregation technique, providing privacy protection for clients against security attacks.</li></ul>

The More is not the Merrier: Investigating the Effect of Client Size on Federated Learning

Discover more