Node Position Encoding
Node Position Encoding is a method in graph representation learning that assigns unique structural identifiers to nodes based on their relative or absolute positions within a graph topology to enhance model awareness of structural relationships.
20
Publications
937
Citations
84
Authors
29
Institutions
Publications per year
2017–2026
18
Parents
20
Heterogeneous Graph Masked Autoencoders
Yijun Tian, Kaiwen Dong, Chunhui Zhang et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2023 · 98 citations · Full text
Rethinking Graph Transformers with Spectral Attention
Devin Kreuzer, Dominique Beaini, William L. Hamilton et al. · arXiv (Cornell University) · 2021 · 70 citations · Full text
1–5 of 20
84
1
h-index
1
h-index
1
h-index
1
h-index
1
h-index
1–5 of 84
29
University of Illinois Urbana-Champaign
Urbana, United States
2 h-index
7 publications
178 citations

McGill University
Montreal, Canada
2 h-index
3 publications
152 citations
Michigan State University
East Lansing, United States
1 h-index
2 publications
66 citations
Austrian Academy of Sciences
Vienna, Austria
1 h-index
4 publications
52 citations

Polytechnique Montréal
Montreal, Canada
1 h-index
1 publications
70 citations
Korea Advanced Institute of Science and Technology
Daejeon, South Korea
1 h-index
1 publications
16 citations

Shandong Normal University
Jinan, China
1 h-index
4 publications
76 citations

Brandeis University
Waltham, United States
1 h-index
2 publications
196 citations
1–8 of 29
Repository · 6 publications · 197 citations
6
h-index
1 publications · 19 citations
2
h-index
1 publications · 37 citations
1
h-index
Conference · 1 publications · 16 citations
1
h-index
Conference · 1 publications · 39 citations
1
h-index
1–5