Results 11 to 20 of about 2,234,265 (385)
Structure of Hsp90–p23–GR reveals the Hsp90 client-remodelling mechanism
Nature, 2021 Chari M Noddings +2 more
exaly +2 more sources
Federated Unlearning: How to Efficiently Erase a Client in FL? [PDF]
arXiv.org, 2022 With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its training data.
Anisa Halimi +3 more
semanticscholar +1 more source
Client Selection in Federated Learning: Principles, Challenges, and Opportunities [PDF]
IEEE Internet of Things Journal, 2022 As a privacy-preserving paradigm for training machine learning (ML) models, federated learning (FL) has received tremendous attention from both industry and academia.
Lei Fu +4 more
semanticscholar +1 more source
Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling [PDF]
IEEE Conference on Computer Communications, 2021 Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server’s communication bandwidth is limited.
Bing Luo +4 more
semanticscholar +1 more source
Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective [PDF]
IEEE Transactions on Wireless Communications, 2020 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 model training using their local data.
Jie Xu, Heqiang Wang
semanticscholar +1 more source
FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning [PDF]
Computer Vision and Pattern Recognition, 2021 Client-wise data heterogeneity is one of the major issues that hinder effective training in federated learning (FL). Since the data distribution on each client may vary dramatically, the client selection strategy can significantly influence the ...
Minxue Tang +6 more
semanticscholar +1 more source
Harm Reduction Journal, 2022 Introduction People who both smoke cigarettes and vape are often considered as a homogenous group even though multiple subgroups may exist. We examined biomarkers of exposure (BOE) and biomarkers of potential harm (BOPH) to differentiate between ...
Pavel N. Lizhnyak +6 more
doaj +1 more source
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge [PDF]
ICC 2019 - 2019 IEEE International Conference on Communications (ICC), 2018 We envision a mobile edge computing (MEC) framework for machine learning (ML) technologies, which leverages distributed client data and computation resources for training high-performance ML models while preserving client privacy. Toward this future goal,
T. Nishio, Ryo Yonetani
semanticscholar +1 more source
An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee [PDF]
IEEE Transactions on Parallel and Distributed Systems, 2020 The issue of potential privacy leakage during centralized AI’s model training has drawn intensive concern from the public. A Parallel and Distributed Computing (or PDC) scheme, termed Federated Learning (FL), has emerged as a new paradigm to cope with ...
Tiansheng Huang +5 more
semanticscholar +1 more source
Health and Quality of Life Outcomes, 2021 Background The harm caused by tobacco use is primarily attributable to cigarette smoking. Switching completely to non-combustible products may reduce disease risks in adult cigarette smokers who are unable or unwilling to quit.
Stacey A. McCaffrey +5 more
doaj +1 more source