Graph Self-supervised Learning
Graph Self-Supervised Learning is a machine learning framework that belongs to the class of self-supervised learning methods, distinguished by its specific design to leverage the structural and relational information inherent in graph-structured data to generate supervisory signals for representation learning without explicit labels.
218
Publications
14.4K
Citations
735
Authors
237
Institutions
Publications per year
2017–2026
218
Variants
Graph Ssl
218
Self-supervised Graph Learning for Recommendation
2021 · 1.3K citations · Full text
Geometry-enhanced molecular representation learning for property prediction
Xiaomin Fang, Lihang Liu, Jieqiong Lei et al. · Nature Machine Intelligence · 2022 · 565 citations · Full text
Graph Self-Supervised Learning: A Survey
Yixin Liu, Ming Jin, Shirui Pan et al. · IEEE Transactions on Knowledge and Data Engineering · 2022 · 495 citations · Full text
1–5 of 218
735
8
h-index
7
h-index
7
h-index
6
h-index
5
h-index
1–5 of 735
237

Peking University
Beijing, China
10 h-index
30 publications
2K citations

Chinese Academy of Sciences
Beijing, China
10 h-index
18 publications
1.3K citations

Monash University
Melbourne, Australia
9 h-index
22 publications
2.3K citations

Beijing University of Posts and Telecommunications
Beijing, China
8 h-index
22 publications
3K citations
Tsinghua University
Beijing, China
8 h-index
21 publications
1.2K citations
University of Chinese Academy of Sciences
Beijing, China
7 h-index
11 publications
279 citations

University of Electronic Science and Technology of China
Chengdu, China
7 h-index
13 publications
788 citations

Xidian University
Xi'an, China
7 h-index
25 publications
2.5K citations
1–8 of 237
Repository · 48 publications · 2.2K citations
25
h-index
10 publications · 371 citations
12
h-index
Conference · 11 publications · 796 citations
11
h-index
TKDE · 8 publications · 1.1K citations
9
h-index
5 publications · 412 citations
7
h-index
1–5