… client privacy. Toward this future goal, this work aims to extend Federated Learning (FL), a
decentralized learning … , to work with heterogeneous clients in a practical cellular network. The …

… of federated learning with biased client selection that is cognizant of the training progress
at each client. We discover that biasing the client selection towards clients with higher local …

… , most assume unbiased client participation, where clients are … analysis of federated learning
with biased client selection … We show that biasing client selection towards clients with higher …

… Learning (ML) models, Federated Learning (FL) has received tremendous attention from both
industry and academia. In a typical FL scenario, clients … Thus, randomly sampling clients in …

… In this paper, we have investigated the client selection problem for federated learning. Our
concern mainly focuses on the tradeoff between fairness factor and training efficiency. In light …

… learning rounds affecting the model accuracy. In this article, we propose FedMCCS, a
multicriteria-based approach for client selection … Yonetani, “Client selection for federated learning …

… Abstract—This paper studies federated learning (FL) in a classic wireless network, where
learning clients share a common wireless link to a coordinating server to perform federated …

… , ie, the larger the divergence with the model trained by IID data, the higher the non-IID
degree of the data in clients. Then, we propose a client selection mechanism, where the clients …

… of available clients are chosen to participate, and the selection decision might have … client
selection problem under a volatile context, in which the local training of heterogeneous clients …

… RQs): • RQ1: What are the main challenges in client selection? • RQ2: How are clients selected
in federated learning? • RQ3: Which metrics are important for measuring client selection? …