Survey of federated learning research
Federated learning has rapidly become a research hotspot in the field of security machine learning in recent years because it can train the global optimal model collaboratively without the need for multiple data source aggregation.Firstly, the federated learning framework, algorithm principle and cl...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2021-10-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021056 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529824129056768 |
|---|---|
| author | Chuanxin ZHOU Yi SUN Degang WANG Huawei GE |
| author_facet | Chuanxin ZHOU Yi SUN Degang WANG Huawei GE |
| author_sort | Chuanxin ZHOU |
| collection | DOAJ |
| description | Federated learning has rapidly become a research hotspot in the field of security machine learning in recent years because it can train the global optimal model collaboratively without the need for multiple data source aggregation.Firstly, the federated learning framework, algorithm principle and classification were summarized.Then, the main threats and challenges it faced, were analysed indepth the comparative analysis of typical research programs in the three directions of communication efficiency, privacy and security, trust and incentive mechanism was focused on, and their advantages and disadvantages were pointed out.Finally, Combined with application of edge computing, blockchain, 5G and other emerging technologies to federated learning, its future development prospects and research hotspots was prospected. |
| format | Article |
| id | doaj-art-c52ecc0a782a46f38afb11ea92b9c8ac |
| institution | Kabale University |
| issn | 2096-109X |
| language | English |
| publishDate | 2021-10-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 网络与信息安全学报 |
| spelling | doaj-art-c52ecc0a782a46f38afb11ea92b9c8ac2025-01-15T03:15:13ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2021-10-017779259568816Survey of federated learning researchChuanxin ZHOUYi SUNDegang WANGHuawei GEFederated learning has rapidly become a research hotspot in the field of security machine learning in recent years because it can train the global optimal model collaboratively without the need for multiple data source aggregation.Firstly, the federated learning framework, algorithm principle and classification were summarized.Then, the main threats and challenges it faced, were analysed indepth the comparative analysis of typical research programs in the three directions of communication efficiency, privacy and security, trust and incentive mechanism was focused on, and their advantages and disadvantages were pointed out.Finally, Combined with application of edge computing, blockchain, 5G and other emerging technologies to federated learning, its future development prospects and research hotspots was prospected.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021056federated learningprivacy protectionblockchainedge of computing |
| spellingShingle | Chuanxin ZHOU Yi SUN Degang WANG Huawei GE Survey of federated learning research 网络与信息安全学报 federated learning privacy protection blockchain edge of computing |
| title | Survey of federated learning research |
| title_full | Survey of federated learning research |
| title_fullStr | Survey of federated learning research |
| title_full_unstemmed | Survey of federated learning research |
| title_short | Survey of federated learning research |
| title_sort | survey of federated learning research |
| topic | federated learning privacy protection blockchain edge of computing |
| url | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021056 |
| work_keys_str_mv | AT chuanxinzhou surveyoffederatedlearningresearch AT yisun surveyoffederatedlearningresearch AT degangwang surveyoffederatedlearningresearch AT huaweige surveyoffederatedlearningresearch |