Graph Attention Networks
Graph Attention Networks is a neural network model that generalizes the attention mechanism to graph-structured data by enabling nodes to attend to their neighbors' features through learnable weighted aggregation, thereby distinguishing itself from other graph neural networks through its adaptive and context-dependent weighting of neighbor contributions.
1.4K
Publications
98.7K
Citations
5.6K
Authors
1K
Institutions
Publications per year
2017–2026
1.4K
Variants
Gats
Parents
1.4K
Guillem Cucurull, Arantxa Casanova, Adriana Romero et al. · arXiv (Cornell University) · 2017 · 8.3K citations · Full text
Heterogeneous Graph Attention Network
Xiao Wang, Houye Ji, Chuan Shi et al. · 2019 · 2.9K citations · Full text
Xiang Wang, Xiangnan He, Yixin Cao et al. · 2019 · 2.1K citations · Full text
1–5 of 1.4K
5.6K
7
h-index
7
h-index
7
h-index
Xinjiang Technical Institute of Physics & Chemistry, China
7 publications · 261 citations
7
h-index
6
h-index
1–5 of 5.6K
1K

Chinese Academy of Sciences
Beijing, China
39 h-index
191 publications
23.8K citations
University of Chinese Academy of Sciences
Beijing, China
33 h-index
110 publications
14.4K citations
Tsinghua University
Beijing, China
29 h-index
134 publications
10.2K citations

Shanghai Jiao Tong University
Shanghai, China
28 h-index
97 publications
10.2K citations

Sun Yat-sen University
Guangzhou, China
28 h-index
111 publications
11.4K citations
Wuhan University
Wuhan, China
26 h-index
120 publications
8.5K citations

Peking University
Beijing, China
26 h-index
83 publications
9.5K citations

Central South University
Changsha, China
25 h-index
105 publications
21.9K citations
1–8 of 1K
Conference · 46 publications · 4.8K citations
31
h-index
Repository · 96 publications · 14K citations
31
h-index
37 publications · 2.7K citations
27
h-index
31 publications · 1.4K citations
24
h-index
35 publications · 1.3K citations
23
h-index
1–5