On multiple kernel learning with multiple labels

Lei Tang, Jianhui Chen, Jieping Ye

Research output: Chapter in Book/Report/Conference proceedingConference contribution

34 Citations (Scopus)

Abstract

For classification with multiple labels, a common approach is to learn a classifier for each label. With a kernel-based classifier, there are two options to set up kernels: select a specific kernel for each label or the same kernel for all labels. In this work, we present a unified framework for multi-label multiple kernel learning, in which the above two approaches can be considered as two extreme cases. Moreover, our framework allows the kernels shared partially among multiple labels, enabling flexible degrees of label commonality. We systematically study how the sharing of kernels among multiple labels affects the performance based on extensive experiments on various benchmark data including images and microarray data. Interesting findings concerning efficacy and efficiency are reported.

Original languageEnglish (US)
Title of host publicationIJCAI International Joint Conference on Artificial Intelligence
Pages1255-1260
Number of pages6
StatePublished - 2009
Event21st International Joint Conference on Artificial Intelligence, IJCAI-09 - Pasadena, CA, United States
Duration: Jul 11 2009Jul 17 2009

Other

Other21st International Joint Conference on Artificial Intelligence, IJCAI-09
CountryUnited States
CityPasadena, CA
Period7/11/097/17/09

Fingerprint

Labels
Classifiers
Microarrays
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Tang, L., Chen, J., & Ye, J. (2009). On multiple kernel learning with multiple labels. In IJCAI International Joint Conference on Artificial Intelligence (pp. 1255-1260)

On multiple kernel learning with multiple labels. / Tang, Lei; Chen, Jianhui; Ye, Jieping.

IJCAI International Joint Conference on Artificial Intelligence. 2009. p. 1255-1260.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tang, L, Chen, J & Ye, J 2009, On multiple kernel learning with multiple labels. in IJCAI International Joint Conference on Artificial Intelligence. pp. 1255-1260, 21st International Joint Conference on Artificial Intelligence, IJCAI-09, Pasadena, CA, United States, 7/11/09.
Tang L, Chen J, Ye J. On multiple kernel learning with multiple labels. In IJCAI International Joint Conference on Artificial Intelligence. 2009. p. 1255-1260
Tang, Lei ; Chen, Jianhui ; Ye, Jieping. / On multiple kernel learning with multiple labels. IJCAI International Joint Conference on Artificial Intelligence. 2009. pp. 1255-1260
@inproceedings{07cef6d9851747249b9d7f00fa334d51,
title = "On multiple kernel learning with multiple labels",
abstract = "For classification with multiple labels, a common approach is to learn a classifier for each label. With a kernel-based classifier, there are two options to set up kernels: select a specific kernel for each label or the same kernel for all labels. In this work, we present a unified framework for multi-label multiple kernel learning, in which the above two approaches can be considered as two extreme cases. Moreover, our framework allows the kernels shared partially among multiple labels, enabling flexible degrees of label commonality. We systematically study how the sharing of kernels among multiple labels affects the performance based on extensive experiments on various benchmark data including images and microarray data. Interesting findings concerning efficacy and efficiency are reported.",
author = "Lei Tang and Jianhui Chen and Jieping Ye",
year = "2009",
language = "English (US)",
isbn = "9781577354260",
pages = "1255--1260",
booktitle = "IJCAI International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - On multiple kernel learning with multiple labels

AU - Tang, Lei

AU - Chen, Jianhui

AU - Ye, Jieping

PY - 2009

Y1 - 2009

N2 - For classification with multiple labels, a common approach is to learn a classifier for each label. With a kernel-based classifier, there are two options to set up kernels: select a specific kernel for each label or the same kernel for all labels. In this work, we present a unified framework for multi-label multiple kernel learning, in which the above two approaches can be considered as two extreme cases. Moreover, our framework allows the kernels shared partially among multiple labels, enabling flexible degrees of label commonality. We systematically study how the sharing of kernels among multiple labels affects the performance based on extensive experiments on various benchmark data including images and microarray data. Interesting findings concerning efficacy and efficiency are reported.

AB - For classification with multiple labels, a common approach is to learn a classifier for each label. With a kernel-based classifier, there are two options to set up kernels: select a specific kernel for each label or the same kernel for all labels. In this work, we present a unified framework for multi-label multiple kernel learning, in which the above two approaches can be considered as two extreme cases. Moreover, our framework allows the kernels shared partially among multiple labels, enabling flexible degrees of label commonality. We systematically study how the sharing of kernels among multiple labels affects the performance based on extensive experiments on various benchmark data including images and microarray data. Interesting findings concerning efficacy and efficiency are reported.

UR - http://www.scopus.com/inward/record.url?scp=78751693089&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751693089&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577354260

SP - 1255

EP - 1260

BT - IJCAI International Joint Conference on Artificial Intelligence

ER -