Transferability Metrics
Transferability Metrics is a quantitative evaluation framework that measures the effectiveness of knowledge transfer from a source task to a target task in transfer learning by assessing performance gains, feature reuse, or representation similarity across domains.
57
Publications
3.2K
Citations
192
Authors
77
Institutions
Publications per year
2017–2026
42
Parents
57
How Transferable are Neural Networks in NLP Applications?
Lili Mou, Meng Zhao, Rui Yan et al. · 2016 · 269 citations · Full text
Jiahua Dong, Yang Cong, Gan Sun et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2021 · 146 citations
Exploring and Predicting Transferability across NLP Tasks
Tu Vu, Tong Wang, Tsendsuren Munkhdalai et al. · 2020 · 105 citations · Full text
An Information-Theoretic Approach to Transferability in Task Transfer Learning
Yajie Bao, Yang Li, Shao‐Lun Huang et al. · 2019 · 102 citations
1–5 of 57
192
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 192
77
Tsinghua University
Beijing, China
4 h-index
7 publications
332 citations
Google (United States)
Mountain View, United States
3 h-index
15 publications
578 citations
Microsoft Research (United Kingdom)
Cambridge, United Kingdom
3 h-index
8 publications
384 citations
National University of Singapore
Singapore, Singapore
2 h-index
2 publications
59 citations

Zhejiang University
Hangzhou, China
2 h-index
8 publications
194 citations

University of Massachusetts Amherst
Amherst Center, United States
2 h-index
5 publications
243 citations
Stanford University
Stanford, United States
2 h-index
3 publications
256 citations
Tsinghua–Berkeley Shenzhen Institute
Shenzhen, China
2 h-index
7 publications
570 citations
1–8 of 77
Repository · 9 publications · 451 citations
9
h-index
Conference · 3 publications · 95 citations
3
h-index
1 publications · 18 citations
2
h-index
TPAMI · 2 publications · 184 citations
2
h-index
1 publications · 22 citations
1
h-index
1–5