Layer-Wise Pruning is a model compression technique that systematically removes parameters from a neural network by applying pruning operations independently and sequentially to individual layers, preserving layer-specific importance characteristics while reducing overall model complexity.
269
Publications
21.8K
Citations
871
Authors
274
Institutions
Publications per year
2017–2026
226
Parents
Publications
269
Channel Pruning for Accelerating Very Deep Neural Networks
Yihui He, Xiangyu Zhang, Jian Sun · 2017 · 2.5K citations
NISP: Pruning Networks Using Neuron Importance Score Propagation
Ruichi Yu, Ang Li, Chun-Fu Chen et al. · 2018 · 851 citations
1–5 of 269
Authors
871
- JH
9
h-index
- GD
8
h-index
- YG
7
h-index
- BZ
7
h-index
- RJ
6
h-index
1–5 of 871
Institutions
274
Tsinghua University
Beijing, China
12 h-index
38 publications
3.6K citations
Peking University
Beijing, China
9 h-index
20 publications
709 citations
Tencent (China)
Shenzhen, China
9 h-index
12 publications
1.7K citations
Nanjing University
Nanjing, China
8 h-index
24 publications
6K citations
Xidian University
Xi'an, China
8 h-index
33 publications
1.1K citations
Zhejiang University
Hangzhou, China
7 h-index
17 publications
1K citations
Chinese Academy of Sciences
Beijing, China
7 h-index
24 publications
966 citations
Beihang University
Beijing, China
7 h-index
13 publications
1.3K citations
1–8 of 274
Venues
- arXiv (Cornell University)
Repository · 64 publications · 4.9K citations
31
h-index
- Neurocomputing
10 publications · 359 citations
10
h-index
- Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 7 publications · 207 citations
7
h-index
- Neural Networks
7 publications · 210 citations
7
h-index
- IEEE Transactions on Neural Networks and Learning Systems
6 publications · 197 citations
6
h-index
1–5