Statistical Heterogeneity
Statistical Heterogeneity is a phenomenon in federated learning characterized by non-independent and non-identically distributed (non-IID) data across clients, where the underlying data distributions differ significantly in their statistical properties, thereby complicating model convergence and generalization.
231
Publications
19.4K
Citations
845
Authors
403
Institutions
Publications per year
2017–2026
149
Parents
231
On the Convergence of FedAvg on Non-IID Data
Xiang Li, Kaixuan Huang, Wenhao Yang et al. · arXiv (Cornell University) · 2019 · 1K citations · Full text
Federated Learning with Personalization Layers
Manoj Ghuhan Arivazhagan, Vinay K. Aggarwal, Aaditya Kumar Singh et al. · arXiv (Cornell University) · 2019 · 520 citations · Full text
1–5 of 231
845
5
h-index
5
h-index
5
h-index
5
h-index
5
h-index
1–5 of 845
403
Duke University
Durham, United States
6 h-index
25 publications
2.1K citations
University of Pennsylvania
Philadelphia, United States
5 h-index
7 publications
520 citations

Peking University
Beijing, China
5 h-index
20 publications
5.8K citations

Shanghai Jiao Tong University
Shanghai, China
5 h-index
23 publications
3K citations
Carnegie Mellon University
Pittsburgh, United States
4 h-index
9 publications
1.1K citations
Nanyang Technological University
Singapore, Singapore
4 h-index
6 publications
282 citations

Cornell University
Ithaca, United States
4 h-index
5 publications
228 citations
Queen's University Belfast
Belfast, United Kingdom
4 h-index
5 publications
583 citations
1–8 of 403
Repository · 35 publications · 4.3K citations
21
h-index
4 publications · 99 citations
4
h-index
Repository · 4 publications · 154 citations
4
h-index
4 publications · 648 citations
4
h-index
3 publications · 398 citations
3
h-index
1–5