FedMP: Federated Learning through Adaptive Model Pruning in Heterogeneous Edge Computing
Author:
Affiliation:
1. School of Computer Science and Technology, University of Science and Technology of China
2. University at Buffalo, The State University of New York,Department of Computer Science and Engineering
Funder
National Key Research and Development Program of China
National Science Foundation of China
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9835153/9835154/09835327.pdf?arnumber=9835327
Reference45 articles.
1. EMNIST: Extending MNIST to handwritten letters
2. Fundamentals of Wireless Communication
3. Cooperative sgd: A unified framework for the design and analysis of communication-efficient sgd algorithms;wang;ArXiv Preprint,2018
4. Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning
5. On the convergence of fedavg on non-iid data;li;ArXiv Preprint,2019
Cited by 27 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 via personalized filter pruning;Information Sciences;2024-09
2. Leveraging local data sampling strategies to improve federated learning;International Journal of Data Science and Analytics;2024-08-29
3. Federated Edge Learning with Blurred or Pseudo Data Sharing;Proceedings of the 53rd International Conference on Parallel Processing;2024-08-12
4. ChronusFed: Reinforcement-Based Adaptive Partial Training for Heterogeneous Federated Learning;Proceedings of the 53rd International Conference on Parallel Processing;2024-08-12
5. Heroes: Lightweight Federated Learning with Neural Composition and Adaptive Local Update in Heterogeneous Edge Networks;IEEE INFOCOM 2024 - IEEE Conference on Computer Communications;2024-05-20
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