Dynamic Sparse Training
Dynamic Sparse Training is a machine learning methodology that iteratively prunes and repurposes network weights during training to maintain sparsity without compromising model performance, distinguished by its adaptive reallocation of connectivity in contrast to static sparse training approaches.
30
Publications
1.4K
Citations
118
Authors
39
Institutions
Publications per year
2017–2026
28
Parents
30
Changlin Li, Guangrun Wang, Bing Wang et al. · 2021 · 137 citations
ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
Haoran You, Zhanyi Sun, Huihong Shi et al. · 2023 · 112 citations
1–5 of 30
118
Eindhoven University of Technology, Netherlands
6 publications · 123 citations
6
h-index
6
h-index
3
h-index
2
h-index
École Polytechnique Fédérale de Lausanne, Switzerland
2 publications · 102 citations
2
h-index
1–5 of 118
39

University of Twente
Enschede, The Netherlands
3 h-index
5 publications
136 citations
Eindhoven University of Technology
Eindhoven, The Netherlands
3 h-index
11 publications
328 citations
University of Illinois Urbana-Champaign
Urbana, United States
2 h-index
6 publications
230 citations
Tsinghua University
Beijing, China
2 h-index
13 publications
306 citations
The University of Texas at Austin
Austin, United States
2 h-index
5 publications
393 citations
Google (United States)
Mountain View, United States
2 h-index
7 publications
249 citations
University of California San Diego
San Diego, United States
2 h-index
2 publications
153 citations
Meta (Israel)
Tel Aviv, Israel
1 h-index
1 publications
37 citations
1–8 of 39
Repository · 9 publications · 395 citations
9
h-index
Conference · 2 publications · 129 citations
2
h-index
1 publications · 13 citations
1
h-index
1 publications · 123 citations
1
h-index
1 publications · 58 citations
1
h-index
1–5