Ranking Support Vector Machine with Kernel Approximation
Kai Chen, Rongchun Li, Yong Dou et al. · Computational Intelligence and Neuroscience · 2017
Learning to rank algorithm has become important in recent years due to its successful application in information retrieval, recommender system, and computational biology, and so forth. Ranking support vector machine (RankSVM) is one of the state-of-art ranking models and has been favorably used. Nonlinear RankSVM (RankSVM with nonlinear kernels) can give higher accuracy than linear RankSVM (RankSVM with a linear kernel) for complex nonlinear ranking problem. However, the learning methods for nonlinear RankSVM are still time-consuming because of the calculation of kernel matrix. In this paper, we propose a fast ranking algorithm based on kernel approximation to avoid computing the kernel matrix. We explore two types of kernel approximation methods, namely, the Nyström method and random Fourier features. Primal truncated Newton method is used to optimize the pairwise L2-loss (squared Hinge-loss) objective function of the ranking model after the nonlinear kernel approximation. Experimental results demonstrate that our proposed method gets a much faster training speed than kernel RankSVM and achieves comparable or better performance over state-of-the-art ranking algorithms.
Cited by 20 works. doi:10.1155/2017/4629534 Open-access PDF
Authors
References
- A training algorithm for optimal margin classifiers
- Modern Information Retrieval
- Optimizing search engines using clickthrough data
- Training linear SVMs in linear time
- Fourier Analysis on Groups
- IR evaluation methods for retrieving highly relevant documents
- Random Features for Large-Scale Kernel Machines
- McRank: Learning to Rank Using Multiple Classification and Gradient Boosting
- Learning to rank
- Learning to Rank for Information Retrieval