Negative Sampling
Negative Sampling is a training strategy in machine learning that belongs to the class of sampling techniques and is distinguished by its selection of a small number of contrasting (negative) examples—typically from a large set of possible non-observed interactions, entity pairs, or document passages—to improve computational efficiency and model discriminability in tasks such as relation extraction, passage retrieval, and implicit feedback modeling.
279
Publications
47.9K
Citations
941
Authors
283
Institutions
Publications per year
2017–2026
247
279
Distributed Representations of Words and Phrases and their Compositionality
Tomáš Mikolov, Ilya Sutskever, Kai Chen et al. · arXiv (Cornell University) · 2013 · 18.1K citations · Full text
Shaosheng Cao, Wei Lu, Qiongkai Xu · 2015 · 1.6K citations
1–5 of 279
941
9
h-index
9
h-index
6
h-index
5
h-index
5
h-index
1–5 of 941
283
Tsinghua University
Beijing, China
23 h-index
97 publications
10.9K citations
Google (United States)
Mountain View, United States
8 h-index
28 publications
85K citations
Microsoft Research (United Kingdom)
Cambridge, United Kingdom
8 h-index
25 publications
563 citations

Chinese Academy of Sciences
Beijing, China
7 h-index
11 publications
366 citations

Peking University
Beijing, China
7 h-index
20 publications
3.8K citations

Beihang University
Beijing, China
7 h-index
23 publications
1.1K citations
University of Science and Technology of China
Hefei, China
7 h-index
23 publications
1.5K citations

Renmin University of China
Beijing, China
7 h-index
12 publications
634 citations
1–8 of 283
Repository · 64 publications · 31.6K citations
27
h-index
Conference · 14 publications · 783 citations
13
h-index
TKDE · 6 publications · 278 citations
6
h-index
4 publications · 97 citations
4
h-index
Conference · 4 publications · 115 citations
4
h-index
1–5