One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes

Author:

Elmahallawy Mohamed1,Luo Tie1

Affiliation:

1. Missouri University of Science and Technology,Department of Computer Science,Rolla,MO,USA,65409

Funder

National Science Foundation

Publisher

IEEE

Reference29 articles.

1. Communication-efficient learning of deep networks from decentralized data;mcmahan;Artificial Intelligence and Statistics,2017

2. Satellite-Based Computing Networks with Federated Learning

3. FedHAP: Fast Federated Learning for LEO Constellations using Collaborative HAPs

4. On-Board Federated Learning for Dense LEO Constellations

5. A practical data-free approach to one-shot federated learning with heterogeneity;zhang;arXiv 2112 12371,2021

Cited by 3 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. Communication-Efficient Federated Learning for LEO Constellations Integrated With HAPs Using Hybrid NOMA-OFDM;IEEE Journal on Selected Areas in Communications;2024-05

2. Secure and Efficient Federated Learning in LEO Constellations Using Decentralized Key Generation and On-Orbit Model Aggregation;GLOBECOM 2023 - 2023 IEEE Global Communications Conference;2023-12-04

3. Crowdsourcing-based Model Testing in Federated Learning;2023 IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom);2023-11-01

同舟云学术

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