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

Abstract : This 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 framework. 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.
Document type :
Conference papers
Complete list of metadatas

Contributor : Lip6 Publications <>
Submitted on : Tuesday, March 29, 2016 - 3:13:46 PM
Last modification on : Thursday, March 21, 2019 - 1:06:52 PM


  • HAL Id : hal-01294607, version 1


Tuong Vinh Truong, Massih-Reza Amini, Patrick Gallinari. A self-training method for learning to rank with unlabeled data. European Symposium on Artificial Neural Networks (ESANN 2009), Apr 2009, Bruges, Belgium. pp.17-22. ⟨hal-01294607⟩



Record views