Speed up SVM-RFE procedure using margin distribution

Yingqin Yuan; Leonid Hrebien; Moshe Kam

doi:10.1109/MLSP.2005.1532917

Speed up SVM-RFE procedure using margin distribution

Yingqin Yuan, Leonid Hrebien, Moshe Kam

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

In this paper, a new method is introduced to speed up the recursive feature ranking procedure by using the margin distribution of a trained SVM. The method, M-RFE, continuously eliminates features without retraining the SVM as long as the margin distribution of the SVM does not change significantly. Synthetic datasets and two benchmark microarray datasets were tested on M-RFE. Comparison with original SVM-RFE shows that our method speeds up the feature ranking procedure considerably with little or no performance degradation. Comparison of M-RFE to a similar speed up technique, E-RFE, provides similar classification performance, but with reduced complexity.

Original language	English (US)
Title of host publication	2005 IEEE Workshop on Machine Learning for Signal Processing
Pages	297-302
Number of pages	6
DOIs	https://doi.org/10.1109/MLSP.2005.1532917
State	Published - 2005
Externally published	Yes
Event	2005 IEEE Workshop on Machine Learning for Signal Processing - Mystic, CT, United States Duration: Sep 28 2005 → Sep 30 2005

Publication series

Name	2005 IEEE Workshop on Machine Learning for Signal Processing

Other

Other	2005 IEEE Workshop on Machine Learning for Signal Processing
Country/Territory	United States
City	Mystic, CT
Period	9/28/05 → 9/30/05

All Science Journal Classification (ASJC) codes

General Engineering

Access to Document

10.1109/MLSP.2005.1532917

Cite this

@inproceedings{f6a42dfbdc08463ea88d3401564fee50,

title = "Speed up SVM-RFE procedure using margin distribution",

abstract = "In this paper, a new method is introduced to speed up the recursive feature ranking procedure by using the margin distribution of a trained SVM. The method, M-RFE, continuously eliminates features without retraining the SVM as long as the margin distribution of the SVM does not change significantly. Synthetic datasets and two benchmark microarray datasets were tested on M-RFE. Comparison with original SVM-RFE shows that our method speeds up the feature ranking procedure considerably with little or no performance degradation. Comparison of M-RFE to a similar speed up technique, E-RFE, provides similar classification performance, but with reduced complexity.",

author = "Yingqin Yuan and Leonid Hrebien and Moshe Kam",

year = "2005",

doi = "10.1109/MLSP.2005.1532917",

language = "English (US)",

isbn = "0780395174",

series = "2005 IEEE Workshop on Machine Learning for Signal Processing",

pages = "297--302",

booktitle = "2005 IEEE Workshop on Machine Learning for Signal Processing",

note = "2005 IEEE Workshop on Machine Learning for Signal Processing ; Conference date: 28-09-2005 Through 30-09-2005",

}

Yuan, Y, Hrebien, L & Kam, M 2005, Speed up SVM-RFE procedure using margin distribution. in 2005 IEEE Workshop on Machine Learning for Signal Processing., 1532917, 2005 IEEE Workshop on Machine Learning for Signal Processing, pp. 297-302, 2005 IEEE Workshop on Machine Learning for Signal Processing, Mystic, CT, United States, 9/28/05. https://doi.org/10.1109/MLSP.2005.1532917

TY - GEN

T1 - Speed up SVM-RFE procedure using margin distribution

AU - Yuan, Yingqin

AU - Hrebien, Leonid

AU - Kam, Moshe

PY - 2005

Y1 - 2005

N2 - In this paper, a new method is introduced to speed up the recursive feature ranking procedure by using the margin distribution of a trained SVM. The method, M-RFE, continuously eliminates features without retraining the SVM as long as the margin distribution of the SVM does not change significantly. Synthetic datasets and two benchmark microarray datasets were tested on M-RFE. Comparison with original SVM-RFE shows that our method speeds up the feature ranking procedure considerably with little or no performance degradation. Comparison of M-RFE to a similar speed up technique, E-RFE, provides similar classification performance, but with reduced complexity.

AB - In this paper, a new method is introduced to speed up the recursive feature ranking procedure by using the margin distribution of a trained SVM. The method, M-RFE, continuously eliminates features without retraining the SVM as long as the margin distribution of the SVM does not change significantly. Synthetic datasets and two benchmark microarray datasets were tested on M-RFE. Comparison with original SVM-RFE shows that our method speeds up the feature ranking procedure considerably with little or no performance degradation. Comparison of M-RFE to a similar speed up technique, E-RFE, provides similar classification performance, but with reduced complexity.

UR - http://www.scopus.com/inward/record.url?scp=33749069293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749069293&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2005.1532917

DO - 10.1109/MLSP.2005.1532917

M3 - Conference contribution

AN - SCOPUS:33749069293

SN - 0780395174

SN - 9780780395176

T3 - 2005 IEEE Workshop on Machine Learning for Signal Processing

SP - 297

EP - 302

BT - 2005 IEEE Workshop on Machine Learning for Signal Processing

T2 - 2005 IEEE Workshop on Machine Learning for Signal Processing

Y2 - 28 September 2005 through 30 September 2005

ER -

Speed up SVM-RFE procedure using margin distribution

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this