Dynamic Graph Features
Dynamic Graph Features is a graph feature engineering methodology that captures evolving structural and attribute-based patterns in temporal graphs by differentiating itself from static graph features through the explicit incorporation of time-varying relationships and node dynamics.
37
Publications
1.7K
Citations
162
Authors
73
Institutions
Publications per year
2017–2026
31
Parents
37
Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
Kuangen Zhang, Ming Hao, Jing Wang et al. · arXiv (Cornell University) · 2019 · 142 citations · Full text
Temporal Graph Networks for Deep Learning on Dynamic Graphs
Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca et al. · arXiv (Cornell University) · 2020 · 95 citations · Full text
Computing, Computer Science, Physics +15
1–5 of 37
162
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 162
73
Nanjing University
Nanjing, China
2 h-index
3 publications
175 citations

Peking University
Beijing, China
2 h-index
4 publications
190 citations

Huazhong University of Science and Technology
Wuhan, China
2 h-index
9 publications
497 citations
University of Pennsylvania
Philadelphia, United States
2 h-index
4 publications
211 citations

South China University of Technology
Guangzhou, China
2 h-index
4 publications
115 citations
University of Chinese Academy of Sciences
Beijing, China
1 h-index
2 publications
262 citations
Laboratoire de Physique de l'ENS de Lyon
Lyon, France
1 h-index
4 publications
68 citations

University of Auckland
Auckland, New Zealand
1 h-index
3 publications
165 citations
1–8 of 73
Repository · 5 publications · 392 citations
5
h-index
Conference · 2 publications · 88 citations
2
h-index
2 publications · 101 citations
2
h-index
1 publications · 21 citations
1
h-index
1 publications · 98 citations
1
h-index
1–5