Multi-Task Meta-Learning is a meta-learning framework that enables a model to acquire shared knowledge across multiple related tasks through meta-training, such that it can rapidly adapt to new tasks with minimal task-specific data by leveraging learned inductive biases.
75
Publications
3.3K
Citations
303
Authors
103
Institutions
Publications per year
2017–2026
73
Parents
Publications
75
LEAF: A Benchmark for Federated Settings
Sebastian Caldas, Peter Wu, Li Tian et al. · arXiv (Cornell University) · 2018 · 285 citations · Full text
Learning a meta-level prior for feature relevance from multiple related tasks
Su-In Lee, Vassil Chatalbashev, David Vickrey et al. · 2007 · 165 citations
Domain Adaptive Dialog Generation via Meta Learning
1–5 of 75
Authors
303
- KB
3
h-index
- CQ
3
h-index
- CK
3
h-index
- SJ
2
h-index
- SL
2
h-index
1–5 of 303
Institutions
103
Chinese Academy of Sciences
Beijing, China
4 h-index
9 publications
501 citations
Carnegie Mellon University
Pittsburgh, United States
4 h-index
11 publications
562 citations
Tsinghua University
Beijing, China
3 h-index
3 publications
52 citations
University of Chinese Academy of Sciences
Beijing, China
3 h-index
5 publications
301 citations
Harbin Institute of Technology
Harbin, China
3 h-index
10 publications
550 citations
GlaxoSmithKline (Netherlands)
Zeist, Netherlands
3 h-index
3 publications
44 citations
Shanghai Jiao Tong University
Shanghai, China
3 h-index
10 publications
173 citations
University of Illinois Urbana-Champaign
Urbana, United States
3 h-index
10 publications
269 citations
1–8 of 103
Venues
- arXiv (Cornell University)
Repository · 22 publications · 1.1K citations
16
h-index
- IEEE Transactions on Affective Computing
TAC · 2 publications · 102 citations
2
h-index
- Sensors
2 publications · 38 citations
2
h-index
- Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 2 publications · 89 citations
2
h-index
- Medical Image Analysis
2 publications · 93 citations
2
h-index
1–5