Research review of federated learning algorithms

In recent years,federated learning has been proposed and received widespread attention to overcome data isolated island challenge.Federated learning related researches were adopted in areas such as financial field,healthcare domain and smart city related application.Federated learning concept was in...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianzong WANG, Lingwei KONG, Zhangcheng HUANG, Linjie CHEN, Yi LIU, Anxun HE, Jing XIAO
Format: Article
Language:zho
Published: China InfoCom Media Group 2020-11-01
Series:大数据
Subjects:
Online Access:http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2020055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212448815022080
author Jianzong WANG
Lingwei KONG
Zhangcheng HUANG
Linjie CHEN
Yi LIU
Anxun HE
Jing XIAO
author_facet Jianzong WANG
Lingwei KONG
Zhangcheng HUANG
Linjie CHEN
Yi LIU
Anxun HE
Jing XIAO
author_sort Jianzong WANG
collection DOAJ
description In recent years,federated learning has been proposed and received widespread attention to overcome data isolated island challenge.Federated learning related researches were adopted in areas such as financial field,healthcare domain and smart city related application.Federated learning concept was introduced into three different layers.The first layer introduced the definition,architecture,classification of federated learning and compared the federated learning with traditional distributed learning.The second layer presented comparison and analysis of federated learning algorithms from machine learning and deep learning aspects.The third layer separated federated learning optimization algorithms into three aspects to optimize federated learning algorithm through reducing communication cost,selecting proper clients and different aggregation method.Finally,the current research status and three main challenges on communication,heterogeneity of system and data to be solved were concluded,and the future prospects in federated learning domain were proposed.
format Article
id doaj-art-400f690f77dc44769da4f348ec539d4b
institution OA Journals
issn 2096-0271
language zho
publishDate 2020-11-01
publisher China InfoCom Media Group
record_format Article
series 大数据
spelling doaj-art-400f690f77dc44769da4f348ec539d4b2025-08-20T02:09:21ZzhoChina InfoCom Media Group大数据2096-02712020-11-0162020055159537360Research review of federated learning algorithmsJianzong WANGLingwei KONGZhangcheng HUANGLinjie CHENYi LIUAnxun HEJing XIAOIn recent years,federated learning has been proposed and received widespread attention to overcome data isolated island challenge.Federated learning related researches were adopted in areas such as financial field,healthcare domain and smart city related application.Federated learning concept was introduced into three different layers.The first layer introduced the definition,architecture,classification of federated learning and compared the federated learning with traditional distributed learning.The second layer presented comparison and analysis of federated learning algorithms from machine learning and deep learning aspects.The third layer separated federated learning optimization algorithms into three aspects to optimize federated learning algorithm through reducing communication cost,selecting proper clients and different aggregation method.Finally,the current research status and three main challenges on communication,heterogeneity of system and data to be solved were concluded,and the future prospects in federated learning domain were proposed.http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2020055federated learning;algorithm optimization;big data;data privacy
spellingShingle Jianzong WANG
Lingwei KONG
Zhangcheng HUANG
Linjie CHEN
Yi LIU
Anxun HE
Jing XIAO
Research review of federated learning algorithms
大数据
federated learning;algorithm optimization;big data;data privacy
title Research review of federated learning algorithms
title_full Research review of federated learning algorithms
title_fullStr Research review of federated learning algorithms
title_full_unstemmed Research review of federated learning algorithms
title_short Research review of federated learning algorithms
title_sort research review of federated learning algorithms
topic federated learning;algorithm optimization;big data;data privacy
url http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2020055
work_keys_str_mv AT jianzongwang researchreviewoffederatedlearningalgorithms
AT lingweikong researchreviewoffederatedlearningalgorithms
AT zhangchenghuang researchreviewoffederatedlearningalgorithms
AT linjiechen researchreviewoffederatedlearningalgorithms
AT yiliu researchreviewoffederatedlearningalgorithms
AT anxunhe researchreviewoffederatedlearningalgorithms
AT jingxiao researchreviewoffederatedlearningalgorithms