Semisupervised multicategory classification with imperfect model

  • Authors:
  • Hong Chen;Luoqing Li

  • Affiliations:
  • Department of Mathematics and Informatics Sciences, College of Science, Huazhong Agricultural University, Wuhan, China and Faculty of Mathematics and Computer Science, Hubei University, Wuhan, Chi ...;Key Laboratory of Applied Mathematics, Hubei Province and the Faculty of Mathematics and Computer Science, Hubei University, Wuhan, China

  • Venue:
  • IEEE Transactions on Neural Networks
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Semisupervised learning has been of growing interest over the past years and many methods have been proposed. While existing semisupervised methods have shown some promising empirical performances, their development has been based largely on heuristics. In this paper, we investigate semisupervised multicategory classification with an imperfect mixture density model. In the proposed model, the training data come from a probability distribution, which can be modeled imperfectly by an identifiable mixture distribution. Furthermore, we propose a semisupervised multicategory classification method and establish its generalization error bounds. The theoretical analysis illustrates that the proposed method can utilize unlabeled data effectively and can achieve fast convergence rate.