A self–training method for learning to rank with with unlabeled data

  1. (PDF, 252 KB)
AuthorSearch for: ; Search for: ; Search for:
Proceedings titleProceedings. European Symposium on Artificial Neural Networks (ESANN 2009)
ConferenceThe 11th European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, April 22-24, 2009
AbstractThis paper presents a new algorithm for bipartite ranking functions trained with partially labeled data. The algorithm is an extension of the self–training paradigm developed under the classification frame- work. We further propose an efficient and scalable optimization method for training linear models though the approach is general in the sense that it can be applied to any classes of scoring functions. Empirical results on several common image and text corpora over the Area Under the ROC Curve (AUC) and the Average Precision measure show that the use of unlabeled data in the training process leads to improve the performance of baseline supervised ranking functions.
Publication date
AffiliationNational Research Council Canada (NRC-CNRC); NRC Institute for Information Technology
Peer reviewedYes
NPARC number16435916
Export citationExport as RIS
Report a correctionReport a correction
Record identifier1f4e0827-4cb1-4865-8e6f-1e87715f8d23
Record created2010-11-24
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)