Unsupervised Variable Selection: when random rankings sound as irrelevancy

Sébastien Guérif
Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008, PMLR 4:163-177, 2008.

Abstract

Whereas the variable selection has been extensively studied in the context of supervised learning, the unsupervised variable selection has attracted attention of researchers more recently as the available amount of unlabeled data has exploded. Many unsupervised variable ranking criteria were proposed and their relevance is usually demonstrated using either external cluster validity indexes or the accuracy of a classifier which are both supervised criteria. Actually, the major issue of the variable subset selection according to a ranking measure has been adressed only by few authors in the unsupervised learning context. In this paper, we propose to combine multiple ranking to go ahead toward a stable consensus variable subset in a totally unsupervised fashion.

Cite this Paper

BibTeX
@InProceedings{pmlr-v4-guerif08a, title = {Unsupervised Variable Selection: when random rankings sound as irrelevancy}, author = {Guérif, Sébastien}, booktitle = {Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008}, pages = {163--177}, year = {2008}, editor = {Saeys, Yvan and Liu, Huan and Inza, Iñaki and Wehenkel, Louis and Pee, Yves Van de}, volume = {4}, series = {Proceedings of Machine Learning Research}, address = {Antwerp, Belgium}, month = {15 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v4/guerif08a/guerif08a.pdf}, url = {https://proceedings.mlr.press/v4/guerif08a.html}, abstract = {Whereas the variable selection has been extensively studied in the context of supervised learning, the unsupervised variable selection has attracted attention of researchers more recently as the available amount of unlabeled data has exploded. Many unsupervised variable ranking criteria were proposed and their relevance is usually demonstrated using either external cluster validity indexes or the accuracy of a classifier which are both supervised criteria. Actually, the major issue of the variable subset selection according to a ranking measure has been adressed only by few authors in the unsupervised learning context. In this paper, we propose to combine multiple ranking to go ahead toward a stable consensus variable subset in a totally unsupervised fashion.} }
Endnote
%0 Conference Paper %T Unsupervised Variable Selection: when random rankings sound as irrelevancy %A Sébastien Guérif %B Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008 %C Proceedings of Machine Learning Research %D 2008 %E Yvan Saeys %E Huan Liu %E Iñaki Inza %E Louis Wehenkel %E Yves Van de Pee %F pmlr-v4-guerif08a %I PMLR %P 163--177 %U https://proceedings.mlr.press/v4/guerif08a.html %V 4 %X Whereas the variable selection has been extensively studied in the context of supervised learning, the unsupervised variable selection has attracted attention of researchers more recently as the available amount of unlabeled data has exploded. Many unsupervised variable ranking criteria were proposed and their relevance is usually demonstrated using either external cluster validity indexes or the accuracy of a classifier which are both supervised criteria. Actually, the major issue of the variable subset selection according to a ranking measure has been adressed only by few authors in the unsupervised learning context. In this paper, we propose to combine multiple ranking to go ahead toward a stable consensus variable subset in a totally unsupervised fashion.
RIS
TY - CPAPER TI - Unsupervised Variable Selection: when random rankings sound as irrelevancy AU - Sébastien Guérif BT - Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008 DA - 2008/09/11 ED - Yvan Saeys ED - Huan Liu ED - Iñaki Inza ED - Louis Wehenkel ED - Yves Van de Pee ID - pmlr-v4-guerif08a PB - PMLR DP - Proceedings of Machine Learning Research VL - 4 SP - 163 EP - 177 L1 - http://proceedings.mlr.press/v4/guerif08a/guerif08a.pdf UR - https://proceedings.mlr.press/v4/guerif08a.html AB - Whereas the variable selection has been extensively studied in the context of supervised learning, the unsupervised variable selection has attracted attention of researchers more recently as the available amount of unlabeled data has exploded. Many unsupervised variable ranking criteria were proposed and their relevance is usually demonstrated using either external cluster validity indexes or the accuracy of a classifier which are both supervised criteria. Actually, the major issue of the variable subset selection according to a ranking measure has been adressed only by few authors in the unsupervised learning context. In this paper, we propose to combine multiple ranking to go ahead toward a stable consensus variable subset in a totally unsupervised fashion. ER -
APA
Guérif, S.. (2008). Unsupervised Variable Selection: when random rankings sound as irrelevancy. Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008, in Proceedings of Machine Learning Research 4:163-177 Available from https://proceedings.mlr.press/v4/guerif08a.html.

Related Material