… FederatedLearning (FL) setup, a number of devices contribute to the training of a common model. We present a method for selecting the devices … , and better device-level performance. …
… lack of any participating devices. In this study, we consider deviceselection based on downlink channels over which the PS shares the global model with the devices. Performing digital …
L Fu, H Zhang, G Gao, M Zhang… - IEEE Internet of Things …, 2023 - ieeexplore.ieee.org
… Abstract—As a privacy-preserving paradigm for training Machine Learning (ML) models, FederatedLearning (FL) has received tremendous attention from both industry and academia. …
T Zhang, KY Lam, J Zhao, F Li, H Han… - … /ACM Transactions on …, 2023 - ieeexplore.ieee.org
… For the deviceselection problem, we train the K-means to perform device clustering while … Then, we carry out deviceselection based on the weight divergence between the local …
… for federatedlearning with partial device participation with any biased client selection strategy. We discover that biasing client selection can speed up the convergence at the rate O( 1 …
H Cho, A Mathur, F Kawsar - Proceedings of the ACM on Interactive …, 2022 - dl.acm.org
… seek to design a federatedlearning approach which respects the privacy of each device’s data and at … We use Oort as a baseline for being the state-of-the-art deviceselection policy that …
X Ji, J Tian, H Zhang, D Wu, T Li - IEEE Internet of Things …, 2023 - ieeexplore.ieee.org
… for each device is different. To solve the above problems for federatedlearning in wireless … longterm FL process with energy-limited edge devices, to reduce the time-averaged cost of …
… machine learning applications. FederatedLearning is thus developed to offer decentralized learning on user devices. However, it is difficult to jointly address multiple issues such as …
H Wang, Z Kaplan, D Niu, B Li - IEEE INFOCOM 2020-IEEE …, 2020 - ieeexplore.ieee.org
… Instead of random selection, we show that selectingdevices with a clustering algorithm can … DRL FOR CLIENT SELECTION We formulate deviceselection for federatedlearning as a …