Abstract | ||
---|---|---|
Learning to rank, a task to learn ranking functions to sort a set of entities using machine learning techniques, has recently attracted much interest in information retrieval and machine learning research. However, most of the existing work conducts a supervised learning fashion. In this paper, we propose a transductive method which extracts paired preference information from the unlabeled test data. Then we design a loss function to incorporate this preference data with the labeled training data, and learn ranking functions by optimizing the loss function via a derived Ranking SVM framework. The experimental results on the LETOR 2.0 benchmark data collections show that our transductive method can significantly outperform the state-of-the-art supervised baseline. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1016/j.eswa.2011.04.076 | Expert Syst. Appl. |
Keywords | Field | DocType |
preference data,information retrieval,supervised learning fashion,transductive method,unlabeled test data,ranking svm,association rule,association rules,ranking function,training data,loss function,learning to rank,benchmark data collection,preference information,transductive learning,data collection,machine learning,supervised learning | Transduction (machine learning),Data mining,Learning to rank,Online machine learning,Semi-supervised learning,Ranking SVM,Computer science,Supervised learning,Unsupervised learning,Preference learning,Artificial intelligence,Machine learning | Journal |
Volume | Issue | ISSN |
38 | 10 | Expert Systems With Applications |
Citations | PageRank | References |
5 | 0.41 | 18 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yan Pan | 1 | 179 | 19.23 |
Hai-Xia Luo | 2 | 17 | 1.26 |
Hongrui Qi | 3 | 5 | 0.41 |
Yong Tang | 4 | 554 | 76.46 |