On multiple kernel learning with multiple labels

Lei Tang, Jianhui Chen, Jieping Ye

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

39 Scopus citations

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-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence
PublisherInternational Joint Conferences on Artificial Intelligence
Pages1255-1260
Number of pages6
ISBN (Print)9781577354260
StatePublished - Jan 1 2009
Event21st International Joint Conference on Artificial Intelligence, IJCAI 2009 - Pasadena, United States
Duration: Jul 11 2009Jul 16 2009

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference21st International Joint Conference on Artificial Intelligence, IJCAI 2009
CountryUnited States
CityPasadena
Period7/11/097/16/09

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'On multiple kernel learning with multiple labels'. Together they form a unique fingerprint.

Cite this