Distance Function Learning
Distance Function Learning is a subfield of Metric Learning that focuses on the algorithmic induction of an optimal distance metric from data, distinguished by its emphasis on learning the distance function itself rather than relying on predefined metrics.
91
Publications
7.5K
Citations
264
Authors
135
Institutions
Publications per year
2017–2026
27
Parents
91
From Word Embeddings To Document Distances
Matt J. Kusner, Yu Sun, Nicholas Kolkin et al. · PolyPublie (École Polytechnique de Montréal) · 2015 · 1.5K citations
Learning distance functions using equivalence relations
Aharon Bar-Hillel, Tomer Hertz, Noam Shental et al. · 2003 · 435 citations
1–5 of 91
264
4
h-index
4
h-index
4
h-index
3
h-index
3
h-index
1–5 of 264
135
Hebrew University of Jerusalem
Jerusalem, Israel
5 h-index
13 publications
2.5K citations

Chinese Academy of Sciences
Beijing, China
5 h-index
12 publications
1.4K citations
Nanyang Technological University
Singapore, Singapore
4 h-index
10 publications
659 citations

Universidad de Granada
Granada, Spain
3 h-index
8 publications
455 citations
Michigan State University
East Lansing, United States
3 h-index
6 publications
550 citations
University of Houston
Houston, United States
3 h-index
11 publications
426 citations
Princeton University
Princeton, United States
3 h-index
3 publications
922 citations

University of Manchester
Manchester, United Kingdom
2 h-index
3 publications
64 citations
1–8 of 135
Repository · 5 publications · 138 citations
5
h-index
3 publications · 233 citations
3
h-index
3 publications · 165 citations
3
h-index
3 publications · 93 citations
3
h-index
3 publications · 170 citations
3
h-index
1–5