creators_name: Tang, Lei
creators_name: Rajan, Suju
creators_name: Narayanan, Vijay K.
type: conference_item
datestamp: 2009-04-06 19:08:57
lastmod: 2009-05-11 09:59:14
metadata_visibility: show
title: Large Scale Multi-Label Classification via MetaLabeler
ispublished: pub
full_text_status: public
pres_type: paper
abstract: The explosion of online content has made the management of such content non-trivial. Web-related tasks such as web page categorization, news filtering, query categorization, tag recommendation, etc. often involve the construction of multilabel categorization systems on a large scale. Existing multilabel classification methods either do not scale or have unsatisfactory performance. In this work, we propose MetaLabeler to automatically determine the relevant set of labels for each instance without intensive human involvement or expensive cross-validation. Extensive experiments conducted on benchmark data show that the MetaLabeler tends to outperform existing methods. Moreover, MetaLabeler scales to millions of multi-labeled instances and can be deployed easily. This enables us to apply the MetaLabeler to a large scale query categorization problem in Yahoo!, yielding a significant improvement in performance.
date: 2009-04
pagerange: 211-211
event_title: 18th International World Wide Web Conference
event_location: Madrid, Spain
event_dates: April 20th-24th, 2009
event_type: conference
refereed: TRUE
citation: Tang, Lei <http://www2009.eprints.org/view/author/Tang=3ALei=3A=3A.html> and Rajan, Suju <http://www2009.eprints.org/view/author/Rajan=3ASuju=3A=3A.html> and Narayanan, Vijay K. <http://www2009.eprints.org/view/author/Narayanan=3AVijay_K=2E=3A=3A.html> (2009) Large Scale Multi-Label Classification via MetaLabeler. In: 18th International World Wide Web Conference, April 20th-24th, 2009, Madrid, Spain.
document_url: http://www2009.eprints.org/22/1/p211.pdf
document_url: http://www2009.eprints.org/22/2/www09-multilabel.pptx