Federated Dropout—A Simple Approach for Enabling Federated Learning on Resource Constrained Devices
Author:
Affiliation:
1. School of Information Science and Technology, ShanghaiTech University, Shanghai, China
2. C&M Standard Laboratory, LG Electronics, Seoul, South Korea
3. Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong
Funder
Fellowship Award from the Research Grants Council of the Hong Kong Special Administrative Region, China
Guang-dong Basic and Applied Basic Research Foundation
Hong Kong Research Grants Council
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Electrical and Electronic Engineering,Control and Systems Engineering
Link
http://xplorestaging.ieee.org/ielx7/5962382/9771304/09707474.pdf?arnumber=9707474
Reference17 articles.
1. Scheduling Policies for Federated Learning in Wireless Networks
2. High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning
3. Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning
4. Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels
5. Distributed optimization of deeply nested systems;carreira-perpinan;Proc Int Workshop Artif Intell Stat (AISTATS),2014
Cited by 41 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. An efficient privacy-preserving and verifiable scheme for federated learning;Future Generation Computer Systems;2024-11
2. Inference Load-Aware Orchestration for Hierarchical Federated Learning;2024 IEEE 49th Conference on Local Computer Networks (LCN);2024-10-08
3. A comprehensive survey on client selection strategies in federated learning;Computer Networks;2024-09
4. Efficient Federated Learning via Joint Communication and Computation Optimization;IEEE Transactions on Vehicular Technology;2024-08
5. Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference;IEEE Transactions on Wireless Communications;2024-08
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3