Fast-Ensembles of Minimum Redundancy Feature Selection
B. Schowe, and K. Morik.. Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet, Kassel, Germany, (2010)
Abstract
Finding relevant subspaces in very high-dimensional data is a challenging task not only for microarray data. The selection of features must be stable, but on the other hand learning performance is to be increased. Ensemble methods have succeeded in the increase of stability and classification accuracy, but their runtime prevents them from scaling up to real-world applications. We propose two methods which enhance correlation-based feature selection such that the stability of feature selection comes with little or even no extra runtime. We show the efficiency of the algorithms analytically and empirically on a wide range of datasets.
%0 Conference Paper
%1 kdml3
%A Schowe, Benjamin
%A Morik., Katharina
%B Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet
%C Kassel, Germany
%D 2010
%E Atzmüller, Martin
%E Benz, Dominik
%E Hotho, Andreas
%E Stumme, Gerd
%K bioinformatics dimensionality ensemble feature methods reduction room:0446 selection session:joint3 workshop:kdml
%T Fast-Ensembles of Minimum Redundancy Feature Selection
%U http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml3.pdf
%X Finding relevant subspaces in very high-dimensional data is a challenging task not only for microarray data. The selection of features must be stable, but on the other hand learning performance is to be increased. Ensemble methods have succeeded in the increase of stability and classification accuracy, but their runtime prevents them from scaling up to real-world applications. We propose two methods which enhance correlation-based feature selection such that the stability of feature selection comes with little or even no extra runtime. We show the efficiency of the algorithms analytically and empirically on a wide range of datasets.
@inproceedings{kdml3,
abstract = {Finding relevant subspaces in very high-dimensional data is a challenging task not only for microarray data. The selection of features must be stable, but on the other hand learning performance is to be increased. Ensemble methods have succeeded in the increase of stability and classification accuracy, but their runtime prevents them from scaling up to real-world applications. We propose two methods which enhance correlation-based feature selection such that the stability of feature selection comes with little or even no extra runtime. We show the efficiency of the algorithms analytically and empirically on a wide range of datasets.},
added-at = {2010-10-05T14:15:12.000+0200},
address = {Kassel, Germany},
author = {Schowe, Benjamin and Morik., Katharina},
biburl = {https://www.bibsonomy.org/bibtex/2c1e726de95ceac405afdf5c2b23b60c5/lwa2010},
booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen {\&} Adaptivitaet},
crossref = {lwa2010},
editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
interhash = {c9a2121b0e6f5b1a380e9cb1dadac310},
intrahash = {c1e726de95ceac405afdf5c2b23b60c5},
keywords = {bioinformatics dimensionality ensemble feature methods reduction room:0446 selection session:joint3 workshop:kdml},
presentation_end = {2010-10-05 12:00:00},
presentation_start = {2010-10-05 11:30:00},
room = {0446},
session = {joint3},
timestamp = {2010-10-05T14:15:14.000+0200},
title = {Fast-Ensembles of Minimum Redundancy Feature Selection},
track = {kdml},
url = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml3.pdf},
year = 2010
}