Task Weighting is a multi-task learning strategy that differentially assigns importance to individual tasks during model optimization to balance their influence on gradient updates, thereby improving overall performance.
51
Publications
5.8K
Citations
170
Authors
68
Institutions
Publications per year
2017–2026
31
Parents
Publications
51
Clustered Multi-Task Learning: a Convex Formulation
Laurent Jacob, Francis Bach · ArXiv.org · 2008 · 175 citations · Full text
A Comparison of Loss Weighting Strategies for Multi task Learning in Deep Neural Networks
Ting Gong, Tyler Lee, Cory Stephenson et al. · IEEE Access · 2019 · 143 citations · Full text
1–5 of 51
Authors
170
- RC
3
h-index
- YG
3
h-index
- AK
3
h-index
- WW
2
h-index
- DL
2
h-index
1–5 of 170
Institutions
68
University of California San Diego
San Diego, United States
3 h-index
4 publications
94 citations
UNSW Sydney
Sydney, Australia
3 h-index
4 publications
210 citations
Carnegie Mellon University
Pittsburgh, United States
3 h-index
7 publications
317 citations
University of Pittsburgh
Pittsburgh, United States
2 h-index
2 publications
158 citations
Brigham and Women's Hospital
Boston, United States
2 h-index
3 publications
240 citations
Ludwig-Maximilians-Universität München
Munich, Germany
2 h-index
5 publications
375 citations
University of Nebraska–Lincoln
Lincoln, United States
2 h-index
5 publications
146 citations
Harvard University
Cambridge, United States
2 h-index
4 publications
316 citations
1–8 of 68
Venues
- arXiv (Cornell University)
Repository · 10 publications · 970 citations
10
h-index
- IEEE Transactions on Pattern Analysis and Machine Intelligence
TPAMI · 2 publications · 145 citations
2
h-index
- Organizational Behavior and Human Performance
2 publications · 45 citations
2
h-index
- Neural Information Processing Systems
Conference · 2 publications · 75 citations
2
h-index
- Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 2 publications · 195 citations
2
h-index
1–5