Many algorithms rely critically on being given a good metric over
their inputs. For instance, data can often be clustered in many "plausible"
ways, and if a clustering algorithm such as K-means initially fails
to find one that is meaningful to a user, the only recourse may be
for the user to manually tweak the metric until sufficiently good
clusters are found. For these and other applications requiring good
metrics, it is desirable that we provide a more systematic way for
users to indicate what they consider "similar." For instance, we
may ask them to provide examples. In this paper, we present an algorithm
that, given examples of similar (and, if desired, dissimilar) pairs
of points in , learns a distance metric over that respects these
relationships. Our method is based on posing metric learning as a
convex optimization problem, which allows us to give efficient, local-optima-free
algorithms. We also demonstrate empirically that the learned metrics
can be used to significantly improve clustering performance.
:Users/guillem/Documents/Doctorat/Bibliografia/articles/Xing et al.\_2002\_Distance Metric Learning, with Application to Clustering with Side-information.pdf:pdf
%0 Journal Article
%1 Xing2002
%A Xing, Eric P
%A Ng, Andrew Y
%A Jordan, Michael I
%A Russell, Stuart
%D 2002
%E in Neural Information Processing Systems 15, Advances
%J MIT Press
%K learning similarity
%P 505--512
%T Distance Metric Learning, with Application to Clustering with Side-information
%X Many algorithms rely critically on being given a good metric over
their inputs. For instance, data can often be clustered in many "plausible"
ways, and if a clustering algorithm such as K-means initially fails
to find one that is meaningful to a user, the only recourse may be
for the user to manually tweak the metric until sufficiently good
clusters are found. For these and other applications requiring good
metrics, it is desirable that we provide a more systematic way for
users to indicate what they consider "similar." For instance, we
may ask them to provide examples. In this paper, we present an algorithm
that, given examples of similar (and, if desired, dissimilar) pairs
of points in , learns a distance metric over that respects these
relationships. Our method is based on posing metric learning as a
convex optimization problem, which allows us to give efficient, local-optima-free
algorithms. We also demonstrate empirically that the learned metrics
can be used to significantly improve clustering performance.
@article{Xing2002,
abstract = {Many algorithms rely critically on being given a good metric over
their inputs. For instance, data can often be clustered in many "plausible"
ways, and if a clustering algorithm such as K-means initially fails
to find one that is meaningful to a user, the only recourse may be
for the user to manually tweak the metric until sufficiently good
clusters are found. For these and other applications requiring good
metrics, it is desirable that we provide a more systematic way for
users to indicate what they consider "similar." For instance, we
may ask them to provide examples. In this paper, we present an algorithm
that, given examples of similar (and, if desired, dissimilar) pairs
of points in , learns a distance metric over that respects these
relationships. Our method is based on posing metric learning as a
convex optimization problem, which allows us to give efficient, local-optima-free
algorithms. We also demonstrate empirically that the learned metrics
can be used to significantly improve clustering performance.},
added-at = {2013-09-29T14:16:50.000+0200},
author = {Xing, Eric P and Ng, Andrew Y and Jordan, Michael I and Russell, Stuart},
biburl = {https://www.bibsonomy.org/bibtex/25d758715bda328af70473b52292f0cb6/guillem.palou},
editor = {{in Neural Information Processing Systems 15}, Advances},
file = {:Users/guillem/Documents/Doctorat/Bibliografia/articles/Xing et al.\_2002\_Distance Metric Learning, with Application to Clustering with Side-information.pdf:pdf},
interhash = {d02a6994d4273046a95ec8dffbc5dc86},
intrahash = {5d758715bda328af70473b52292f0cb6},
journal = {MIT Press},
keywords = {learning similarity},
pages = {505--512},
timestamp = {2013-09-29T14:16:50.000+0200},
title = {{Distance Metric Learning, with Application to Clustering with Side-information}},
year = 2002
}