FSMRank: Feature Selection Algorithm for Learning to Rank
Authors:
- 8 March 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 24 (6) , 940-952
Abstract
In recent years, there has been growing interest in learning to rank. The introduction of feature selection into different learning problems has been proven effective. These facts motivate us to investigate the problem of feature selection for learning to rank. We propose a joint convex optimization formulation which minimizes ranking errors while simultaneously conducting feature selection. This optimization formulation provides a flexible framework in which we can easily incorporate various importance measures and similarity measures of the features. To solve this optimization problem, we use the Nesterov's approach to derive an accelerated gradient algorithm with a fast convergence rate O(1/T2). We further develop a generalization bound for the proposed optimization problem using the Rademacher complexities. Extensive experimental evaluations are conducted on the public LETOR benchmark datasets. The results demonstrate that the proposed method shows: 1) significant ranking performance gain compared to several feature selection baselines for ranking, and 2) very competitive performance compared to several state-of-the-art learning-to-rank algorithms.Keywords
This publication has 23 references indexed in Scilit:
- Improving the ranking quality of medical image retrieval using a genetic feature selection methodDecision Support Systems, 2011
- Greedy and Randomized Feature Selection for Web Search Ranking2011
- SortNet: Learning to Rank by a Neural Preference FunctionIEEE Transactions on Neural Networks, 2011
- Feature selection under learning to rank model for multimedia retrieve2010
- Large-scale sparse logistic regression2009
- An accelerated gradient method for trace norm minimization2009
- Fast Solution of $\ell _{1}$-Norm Minimization Problems When the Solution May Be SparseIEEE Transactions on Information Theory, 2008
- Training linear SVMs in linear time2006
- Introductory Lectures on Convex Optimization2004
- 10.1162/153244303322753698Applied Physics Letters, 2000