Introducing diversity among the models of multi-label classification ensemble

Lena Chekina; Lior Rokach; Bracha Shapira

Introducing diversity among the models of multi-label classification ensemble

Lena Chekina, Lior Rokach, Bracha Shapira

Department of Software and Information Systems Engineering

Ben-Gurion University of the Negev

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

Abstract

A number of ensemble algorithms for solving multi-label classification problems have been proposed in recent years. Diversity among the base learners is known to be important for constructing a good ensemble. In this paper we define a method for introducing diversity among the base learners of one of the previously presented multi-label ensemble classifiers. An empirical comparison on 10 datasets demonstrates that model diversity leads to an improvement in prediction accuracy in 80% of the evaluated cases. Additionally, in most cases the proposed “diverse” ensemble method outperforms other multi-label ensembles as well.

Original language	American English
Title of host publication	ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Pages	239-244
Number of pages	6
State	Published - 1 Jan 2012
Event	20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012 - Bruges, Belgium Duration: 25 Apr 2012 → 27 Apr 2012

Publication series

Name	ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Conference

Conference	20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012
Country/Territory	Belgium
City	Bruges
Period	25/04/12 → 27/04/12

All Science Journal Classification (ASJC) codes

Information Systems
Artificial Intelligence

Cite this

Chekina, L., Rokach, L., & Shapira, B. (2012). Introducing diversity among the models of multi-label classification ensemble. In ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (pp. 239-244). (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning).

Chekina, Lena ; Rokach, Lior ; Shapira, Bracha. / Introducing diversity among the models of multi-label classification ensemble. ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 2012. pp. 239-244 (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning).

@inproceedings{1ff2a6a949d84159b736ed46b7c79614,

title = "Introducing diversity among the models of multi-label classification ensemble",

abstract = "A number of ensemble algorithms for solving multi-label classification problems have been proposed in recent years. Diversity among the base learners is known to be important for constructing a good ensemble. In this paper we define a method for introducing diversity among the base learners of one of the previously presented multi-label ensemble classifiers. An empirical comparison on 10 datasets demonstrates that model diversity leads to an improvement in prediction accuracy in 80\% of the evaluated cases. Additionally, in most cases the proposed “diverse” ensemble method outperforms other multi-label ensembles as well.",

author = "Lena Chekina and Lior Rokach and Bracha Shapira",

note = "Publisher Copyright: {\textcopyright} 2012, i6doc.com publication. All rights reserved.; 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012 ; Conference date: 25-04-2012 Through 27-04-2012",

year = "2012",

month = jan,

day = "1",

language = "American English",

isbn = "9782874190490",

series = "ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

pages = "239--244",

booktitle = "ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

}

Chekina, L, Rokach, L & Shapira, B 2012, Introducing diversity among the models of multi-label classification ensemble. in ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 239-244, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012, Bruges, Belgium, 25/04/12.

Introducing diversity among the models of multi-label classification ensemble. / Chekina, Lena; Rokach, Lior ; Shapira, Bracha.
ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 2012. p. 239-244 (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning).

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

TY - GEN

T1 - Introducing diversity among the models of multi-label classification ensemble

AU - Chekina, Lena

AU - Rokach, Lior

AU - Shapira, Bracha

PY - 2012/1/1

Y1 - 2012/1/1

N2 - A number of ensemble algorithms for solving multi-label classification problems have been proposed in recent years. Diversity among the base learners is known to be important for constructing a good ensemble. In this paper we define a method for introducing diversity among the base learners of one of the previously presented multi-label ensemble classifiers. An empirical comparison on 10 datasets demonstrates that model diversity leads to an improvement in prediction accuracy in 80% of the evaluated cases. Additionally, in most cases the proposed “diverse” ensemble method outperforms other multi-label ensembles as well.

AB - A number of ensemble algorithms for solving multi-label classification problems have been proposed in recent years. Diversity among the base learners is known to be important for constructing a good ensemble. In this paper we define a method for introducing diversity among the base learners of one of the previously presented multi-label ensemble classifiers. An empirical comparison on 10 datasets demonstrates that model diversity leads to an improvement in prediction accuracy in 80% of the evaluated cases. Additionally, in most cases the proposed “diverse” ensemble method outperforms other multi-label ensembles as well.

UR - http://www.scopus.com/inward/record.url?scp=84947799891&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9782874190490

T3 - ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

SP - 239

EP - 244

BT - ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

T2 - 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012

Y2 - 25 April 2012 through 27 April 2012

ER -

Chekina L, Rokach L , Shapira B. Introducing diversity among the models of multi-label classification ensemble. In ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 2012. p. 239-244. (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning).

Introducing diversity among the models of multi-label classification ensemble

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this