Graph Convolutional Networks
Graph Convolutional Networks is a type of neural network model designed for graph-structured data that generalizes convolutional operations to non-Euclidean domains by propagating and aggregating node features through localized spectral filtering over the graph topology.
3.9K
Publications
331.8K
Citations
13.6K
Authors
2.2K
Institutions
Publications per year
2017–2026
3.9K
Variants
Graph Convolutional Network
Parents
3.9K
Dynamic Graph CNN for Learning on Point Clouds
Yue Wang, Yongbin Sun, Ziwei Liu et al. · ACM Transactions on Graphics · 2019 · 6.7K citations · Full text
1–5 of 3.9K
13.6K
17
h-index
16
h-index
16
h-index
15
h-index
15
h-index
1–5 of 13.6K
2.2K

Chinese Academy of Sciences
Beijing, China
57 h-index
479 publications
53.4K citations
Tsinghua University
Beijing, China
54 h-index
333 publications
38.2K citations

Peking University
Beijing, China
49 h-index
290 publications
100.1K citations
University of Chinese Academy of Sciences
Beijing, China
47 h-index
297 publications
39.4K citations

Beijing University of Posts and Telecommunications
Beijing, China
40 h-index
244 publications
18.4K citations
University of Science and Technology of China
Hefei, China
40 h-index
206 publications
15K citations

Shanghai Jiao Tong University
Shanghai, China
39 h-index
247 publications
18.2K citations

Zhejiang University
Hangzhou, China
37 h-index
165 publications
13.9K citations
1–8 of 2.2K
Repository · 400 publications · 34.3K citations
75
h-index
Conference · 127 publications · 29.2K citations
63
h-index
57 publications · 8.8K citations
41
h-index
60 publications · 6K citations
36
h-index
59 publications · 3.3K citations
34
h-index
1–5