Detail publikace

Manifold regularized multiple kernel learning with Hellinger distance

YANG, T. FU, D. LI, X. ŘÍHA, K.

Originální název

Manifold regularized multiple kernel learning with Hellinger distance

Anglický název

Manifold regularized multiple kernel learning with Hellinger distance

Jazyk

en

Originální abstrakt

The aim of this paper is to solve the problem of unsupervised manifold regularization being used under supervised classification circumstance. This paper not only considers that the manifold information of data can provide useful information but also proposes a supervised method to compute the Laplacian graph by using the label information and the Hellinger distance for a comprehensive evaluation of the similarity of data samples. Meanwhile, multi-source or complex data is increasing nowadays. It is desirable to learn from several kernels that are adaptable and flexible to deal with this type of data. Therefore, our classifier is based on multiple kernel learning, and the proposed approach to supervised classification is a multiple kernel model with manifold regularization to incorporate intrinsic geometrical information. Finally, a classifier that minimizes the testing error and considers the geometrical structure of data is put forward. The results of experiments with other methods show the effectiveness of the proposed model and computing the inner potential geometrical information is useful for classification.

Anglický abstrakt

The aim of this paper is to solve the problem of unsupervised manifold regularization being used under supervised classification circumstance. This paper not only considers that the manifold information of data can provide useful information but also proposes a supervised method to compute the Laplacian graph by using the label information and the Hellinger distance for a comprehensive evaluation of the similarity of data samples. Meanwhile, multi-source or complex data is increasing nowadays. It is desirable to learn from several kernels that are adaptable and flexible to deal with this type of data. Therefore, our classifier is based on multiple kernel learning, and the proposed approach to supervised classification is a multiple kernel model with manifold regularization to incorporate intrinsic geometrical information. Finally, a classifier that minimizes the testing error and considers the geometrical structure of data is put forward. The results of experiments with other methods show the effectiveness of the proposed model and computing the inner potential geometrical information is useful for classification.

Dokumenty

BibTex


@article{BUT161347,
  author="Tao {Yang} and Dongmei {Fu} and Xiaogang {Li} and Kamil {Říha}",
  title="Manifold regularized multiple kernel learning with Hellinger distance",
  annote="The aim of this paper is to solve the problem of unsupervised manifold regularization being used under supervised classification circumstance. This paper not only considers that the manifold information of data can provide useful information but also proposes a supervised method to compute the Laplacian graph by using the label information and the Hellinger distance for a comprehensive evaluation of the similarity of data samples. Meanwhile, multi-source or complex data is increasing nowadays. It is desirable to learn from several kernels that are adaptable and flexible to deal with this type of data. Therefore, our classifier is based on multiple kernel learning, and the proposed approach to supervised classification is a multiple kernel model with manifold regularization to incorporate intrinsic geometrical information. Finally, a classifier that minimizes the testing error and considers the geometrical structure of data is put forward. The results of experiments with other methods show the effectiveness of the proposed model and computing the inner potential geometrical information is useful for classification.",
  address="SPRINGER",
  chapter="161347",
  doi="10.1007/s10586-018-2106-2",
  institution="SPRINGER",
  number="6",
  volume="22",
  year="2019",
  month="november",
  pages="13843--13851",
  publisher="SPRINGER",
  type="journal article in Web of Science"
}