Meta-learning Optimization
Meta-Learning Optimization is a computational framework within machine learning that enables the automatic adaptation of optimization algorithms by leveraging knowledge acquired across multiple learning tasks to improve learning efficiency and generalization in novel tasks.
207
Publications
14.6K
Citations
774
Authors
294
Institutions
Publications per year
2017–2026
172
207
Low-Shot Learning from Imaginary Data
Yu-Xiong Wang, Ross Girshick, Martial Hebert et al. · 2018 · 763 citations
A survey of deep meta-learning
Artificial Intelligence Review · 2021 · 358 citations · Full text
1–5 of 207
774
9
h-index
7
h-index
4
h-index
4
h-index
3
h-index
1–5 of 774
294
Universidade de São Paulo
São Paulo, Brazil
9 h-index
21 publications
1.3K citations
Tsinghua University
Beijing, China
8 h-index
10 publications
595 citations
University of Chinese Academy of Sciences
Beijing, China
8 h-index
24 publications
1.4K citations

Universidade do Porto
Porto, Portugal
7 h-index
8 publications
714 citations

Chinese Academy of Sciences
Beijing, China
7 h-index
27 publications
1.2K citations
Google (United States)
Mountain View, United States
6 h-index
10 publications
913 citations

Universidade Federal de Pernambuco
Recife, Brazil
5 h-index
9 publications
693 citations

Shanghai Jiao Tong University
Shanghai, China
5 h-index
19 publications
392 citations
1–8 of 294
Repository · 28 publications · 827 citations
17
h-index
11 publications · 1.1K citations
11
h-index
8 publications · 177 citations
7
h-index
4 publications · 200 citations
4
h-index
4 publications · 142 citations
4
h-index
1–5