Graph-based Semi-supervised Learning
Graph-Based Semi-Supervised Learning is a semi-supervised learning paradigm that leverages a graph structure to model relationships among data points, where the graph's nodes represent labeled and unlabeled instances and edges encode pairwise similarities, enabling label propagation from labeled to unlabeled data through the graph's topology.
545
Publications
34.6K
Citations
1.6K
Authors
512
Institutions
Publications per year
2017–2026
299
Parents
545
A Survey on Deep Semi-Supervised Learning
Xiangli Yang, Zixing Song, Irwin King et al. · IEEE Transactions on Knowledge and Data Engineering · 2022 · 828 citations
Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
Yunsheng Shi, Zhengjie Huang, Shikun Feng et al. · 2021 · 643 citations · Full text
1–5 of 545
1.6K
19
h-index
10
h-index
10
h-index
9
h-index
9
h-index
1–5 of 1.6K
512

Northwestern Polytechnical University
Xi'an, China
19 h-index
53 publications
2.7K citations
University of Science and Technology of China
Hefei, China
18 h-index
66 publications
3.8K citations
Microsoft Research Asia (China)
Beijing, China
17 h-index
36 publications
3.1K citations
Tsinghua University
Beijing, China
17 h-index
52 publications
4.1K citations

Chinese Academy of Sciences
Beijing, China
15 h-index
40 publications
2.6K citations
Carnegie Mellon University
Pittsburgh, United States
14 h-index
34 publications
2.5K citations

City University of Hong Kong
Hong Kong, Hong Kong
14 h-index
32 publications
1.1K citations

Shanghai Jiao Tong University
Shanghai, China
13 h-index
26 publications
1.4K citations
1–8 of 512
Repository · 45 publications · 2.4K citations
23
h-index
16 publications · 760 citations
14
h-index
TKDE · 14 publications · 1.8K citations
14
h-index
14 publications · 636 citations
13
h-index
14 publications · 268 citations
12
h-index
1–5