Positive-unlabeled Learning
Positive-Unlabeled Learning is a machine learning paradigm in which a classifier is trained using only positive and unlabeled data, differing from standard supervised learning by the absence of explicitly negative labels and relying on assumptions to infer the latent structure of the unlabeled data.
179
Publications
11.4K
Citations
625
Authors
282
Institutions
Publications per year
2017–2026
121
Parents
179
Learning classifiers from only positive and unlabeled data
Charles Elkan, Keith Noto · 2008 · 1K citations
Building text classifiers using positive and unlabeled examples
Learning from positive and unlabeled data: a survey
Machine Learning · 2020 · 515 citations · Full text
Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback
Yuta Saito, Suguru Yaginuma, Yuta Nishino et al. · 2020 · 288 citations
1–5 of 179
625
9
h-index
7
h-index
6
h-index
6
h-index
5
h-index
1–5 of 625
282
The University of Tokyo
Tokyo, Japan
10 h-index
28 publications
1.4K citations

The University of Sydney
Sydney, Australia
8 h-index
20 publications
937 citations
University of Technology Sydney
Sydney, Australia
8 h-index
18 publications
921 citations

Chinese Academy of Sciences
Beijing, China
6 h-index
9 publications
219 citations
Institute for Infocomm Research
Singapore, Singapore
6 h-index
16 publications
1.8K citations
Northwest A&F University
Yangling, China
6 h-index
13 publications
303 citations
Nanyang Technological University
Singapore, Singapore
6 h-index
16 publications
1.5K citations
University of Illinois Chicago
Chicago, United States
5 h-index
12 publications
2.4K citations
1–8 of 282
Repository · 9 publications · 328 citations
9
h-index
8 publications · 303 citations
8
h-index
Conference · 6 publications · 241 citations
6
h-index
5 publications · 129 citations
5
h-index
4 publications · 126 citations
4
h-index
1–5