Applied Intelligence

, Volume 40, Issue 4, pp 623–638

Manifold proximal support vector machine for semi-supervised classification

  • Wei-Jie Chen
  • Yuan-Hai Shao
  • Deng-Ke Xu
  • Yong-Feng Fu
Article

DOI: 10.1007/s10489-013-0491-z

Cite this article as:
Chen, WJ., Shao, YH., Xu, DK. et al. Appl Intell (2014) 40: 623. doi:10.1007/s10489-013-0491-z

Abstract

Recently, semi-supervised learning (SSL) has attracted a great deal of attention in the machine learning community. Under SSL, large amounts of unlabeled data are used to assist the learning procedure to construct a more reasonable classifier. In this paper, we propose a novel manifold proximal support vector machine (MPSVM) for semi-supervised classification. By introducing discriminant information in the manifold regularization (MR), MPSVM not only introduces MR terms to capture as much geometric information as possible from inside the data, but also utilizes the maximum distance criterion to characterize the discrepancy between different classes, leading to the solution of a pair of eigenvalue problems. In addition, an efficient particle swarm optimization (PSO)-based model selection approach is suggested for MPSVM. Experimental results on several artificial as well as real-world datasets demonstrate that MPSVM obtains significantly better performance than supervised GEPSVM, and achieves comparable or better performance than LapSVM and LapTSVM, with better learning efficiency.

Keywords

Semi-supervised classificationManifold regularizationSupport vector machineNonparallel hyperplanesParticle swarm optimization

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Wei-Jie Chen
    • 1
  • Yuan-Hai Shao
    • 1
  • Deng-Ke Xu
    • 2
  • Yong-Feng Fu
    • 1
  1. 1.Zhijiang CollegeZhejiang University of TechnologyHangzhouP.R. China
  2. 2.Department of StatisticsZhejiang Agriculture and Forest UniversityLin’anP.R. China