Federated Learning: A Distributed Shared Machine Learning Method
Federated learning (FL) is a distributed machine learning (ML) framework. In FL, multiple clients collaborate to solve traditional distributed ML problems under the coordination of the central server without sharing their local private data with others. This paper mainly sorts out FLs based on machi...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2021-01-01
|
Series: | Complexity |
Online Access: | http://dx.doi.org/10.1155/2021/8261663 |
id |
doaj-7ea56d3aa0b2447ea8a0ce24f99106f6 |
---|---|
record_format |
Article |
spelling |
doaj-7ea56d3aa0b2447ea8a0ce24f99106f62021-09-13T01:24:17ZengHindawi-WileyComplexity1099-05262021-01-01202110.1155/2021/8261663Federated Learning: A Distributed Shared Machine Learning MethodKai Hu0Yaogen Li1Min Xia2Jiasheng Wu3Meixia Lu4Shuai Zhang5Liguo Weng6Nanjing University of Information Science & TechnologyNanjing University of Information Science & TechnologyNanjing University of Information Science & TechnologyNanjing University of Information Science & TechnologyNanjing University of Information Science & TechnologyNanjing University of Information Science & TechnologyNanjing University of Information Science & TechnologyFederated learning (FL) is a distributed machine learning (ML) framework. In FL, multiple clients collaborate to solve traditional distributed ML problems under the coordination of the central server without sharing their local private data with others. This paper mainly sorts out FLs based on machine learning and deep learning. First of all, this paper introduces the development process, definition, architecture, and classification of FL and explains the concept of FL by comparing it with traditional distributed learning. Then, it describes typical problems of FL that need to be solved. On the basis of classical FL algorithms, several federated machine learning algorithms are briefly introduced, with emphasis on deep learning and classification and comparisons of those algorithms are carried out. Finally, this paper discusses possible future developments of FL based on deep learning.http://dx.doi.org/10.1155/2021/8261663 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kai Hu Yaogen Li Min Xia Jiasheng Wu Meixia Lu Shuai Zhang Liguo Weng |
spellingShingle |
Kai Hu Yaogen Li Min Xia Jiasheng Wu Meixia Lu Shuai Zhang Liguo Weng Federated Learning: A Distributed Shared Machine Learning Method Complexity |
author_facet |
Kai Hu Yaogen Li Min Xia Jiasheng Wu Meixia Lu Shuai Zhang Liguo Weng |
author_sort |
Kai Hu |
title |
Federated Learning: A Distributed Shared Machine Learning Method |
title_short |
Federated Learning: A Distributed Shared Machine Learning Method |
title_full |
Federated Learning: A Distributed Shared Machine Learning Method |
title_fullStr |
Federated Learning: A Distributed Shared Machine Learning Method |
title_full_unstemmed |
Federated Learning: A Distributed Shared Machine Learning Method |
title_sort |
federated learning: a distributed shared machine learning method |
publisher |
Hindawi-Wiley |
series |
Complexity |
issn |
1099-0526 |
publishDate |
2021-01-01 |
description |
Federated learning (FL) is a distributed machine learning (ML) framework. In FL, multiple clients collaborate to solve traditional distributed ML problems under the coordination of the central server without sharing their local private data with others. This paper mainly sorts out FLs based on machine learning and deep learning. First of all, this paper introduces the development process, definition, architecture, and classification of FL and explains the concept of FL by comparing it with traditional distributed learning. Then, it describes typical problems of FL that need to be solved. On the basis of classical FL algorithms, several federated machine learning algorithms are briefly introduced, with emphasis on deep learning and classification and comparisons of those algorithms are carried out. Finally, this paper discusses possible future developments of FL based on deep learning. |
url |
http://dx.doi.org/10.1155/2021/8261663 |
work_keys_str_mv |
AT kaihu federatedlearningadistributedsharedmachinelearningmethod AT yaogenli federatedlearningadistributedsharedmachinelearningmethod AT minxia federatedlearningadistributedsharedmachinelearningmethod AT jiashengwu federatedlearningadistributedsharedmachinelearningmethod AT meixialu federatedlearningadistributedsharedmachinelearningmethod AT shuaizhang federatedlearningadistributedsharedmachinelearningmethod AT liguoweng federatedlearningadistributedsharedmachinelearningmethod |
_version_ |
1717381604557455360 |