Resource-aware Pruning
Resource-Aware Pruning is a model compression technique that selectively removes parameters from neural networks based on an explicit optimization of computational, memory, or energy constraints to achieve efficient inference while preserving model performance.
47
Publications
3.2K
Citations
178
Authors
79
Institutions
Publications per year
2017–2026
44
Parents
47
Once-for-All: Train One Network and Specialize it for Efficient\n Deployment
Han Cai, Chuang Gan, Tianzhe Wang et al. · arXiv (Cornell University) · 2019 · 682 citations · Full text
Shuo Wang, Zhe Li, Caiwen Ding et al. · 2018 · 226 citations · Full text
1–5 of 47
178
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 178
79
Massachusetts Institute of Technology
Cambridge, United States
3 h-index
6 publications
550 citations
Tsinghua University
Beijing, China
3 h-index
9 publications
440 citations

Shanghai Jiao Tong University
Shanghai, China
3 h-index
4 publications
202 citations

Peking University
Beijing, China
2 h-index
3 publications
482 citations

Chinese Academy of Sciences
Beijing, China
2 h-index
8 publications
235 citations
Simon Fraser University
Burnaby, Canada
2 h-index
3 publications
540 citations
Nanyang Technological University
Singapore, Singapore
2 h-index
3 publications
59 citations
Arizona State University
Tempe, United States
2 h-index
3 publications
58 citations
1–8 of 79
Repository · 14 publications · 1.6K citations
13
h-index
3 publications · 45 citations
3
h-index
3 publications · 92 citations
3
h-index
TPAMI · 1 publications · 143 citations
1
h-index
IMWUT · 1 publications · 25 citations
1
h-index
1–5