Cross-silo Federated Learning
Cross-Silo Federated Learning is a federated learning paradigm in which multiple organizations or institutions collaboratively train a shared model while maintaining data isolation, with each participant functioning as a distinct data silo and contributing data or models under coordinated aggregation, distinguished from other federated learning approaches by its focus on inter-organizational collaboration involving relatively few, data-rich participants.
44
Publications
2.5K
Citations
201
Authors
69
Institutions
Publications per year
2017–2026
44
Parents
44
1–5 of 44
201
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 201
69

Sun Yat-sen University
Guangzhou, China
2 h-index
4 publications
194 citations

Beijing Institute of Technology
Beijing, China
2 h-index
3 publications
64 citations

Hong Kong University of Science and Technology
Hong Kong, Hong Kong
2 h-index
5 publications
1.2K citations
Simon Fraser University
Burnaby, Canada
2 h-index
6 publications
2.1K citations
Shandong University
Jinan, China
2 h-index
5 publications
146 citations

University of Toronto
Toronto, Canada
2 h-index
5 publications
118 citations
Huawei Technologies (Canada)
Markham, Canada
2 h-index
6 publications
2.1K citations

McMaster University
Hamilton, Canada
2 h-index
2 publications
696 citations
1–8 of 69
Repository · 9 publications · 249 citations
9
h-index
4 publications · 120 citations
4
h-index
2 publications · 59 citations
2
h-index
Conference · 2 publications · 681 citations
2
h-index
1 publications · 59 citations
1
h-index
1–5