… Motivated by the limitations of existing works, in this work, we propose PyramidFL, a ne-grained
client selection-based FL framework that enhances the federated training e ciency. The …

… rounds of federated learning, where we vary the number of clients with 70% of mislabeled
data among 10 participating clients. It can be easily seen that the global learning performance …

… paradigm for training Machine Learning (ML) models, Federated Learning (… In a typical FL
scenario, clients exhibit significant … Thus, randomly sampling clients in each training round may …

… Inspired by the recent success of Multi Agent Reinforcement Learning (MARL) in … , a federated
learning framework that relies on trained MARL agents to perform efficient client selection. …

… unbiased client participation, where clients are selected such … analysis of federated learning
with biased client selection and … We show that biasing client selection towards clients with …

… Client selection for federated learning with heterogeneous resources in mobile edge. In
ICC 2019 - 2019 IEEE International Conference on Communications (ICC), pages 1–7, 2019. …

… high-performance ML models while preserving client privacy. Toward this future … Federated
Learning (FL), a decentralized learning framework that enables privacy-preserving training of …

… 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? …

… efficiency. In this paper, we propose Oort to improve the performance of federated training and
… performance in model training, Oort prioritizes the use of those clients who have both data …

… , federated learning (FL) is nowadays a game changer addressing both privacy and cooperative
learning… Yonetani, “Client selection for federated learning with heterogeneous resources …