Experimenting With Normalization Layers in Federated Learning on Non-IID Scenarios

Author:

Casella Bruno1ORCID,Esposito Roberto1ORCID,Sciarappa Antonio2,Cavazzoni Carlo2,Aldinucci Marco1

Affiliation:

1. Department of Computer Science, University of Turin, Turin, Italy

2. Leonardo S.p.A., Rome, Italy

Funder

Spoke “FutureHPC & BigData” of the ICSC–Centro Nazionale di Ricerca in “High Performance Computing, Big Data and Quantum Computing,”

European Union–NextGenerationEU

European Union within the H2020 RIA “European Processor Initiative—Specific Grant Agreement 2”

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Reference35 articles.

1. Advances and Open Problems in Federated Learning

2. Data Sharing in a Time of Pandemic

3. The EU General Data Protection Regulation (GDPR)

4. Communication-efficient learning of deep networks from decentralized data;McMahan

5. On the convergence of FedAvg on non-IID data;Li;arXiv:1907.02189,2019

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