Semi-Supervised Local Fisher Discriminant Analysis for Dimensionality Reduction

  • Masashi Sugiyama
  • Tsuyoshi Idé
  • Shinichi Nakajima
  • Jun Sese
Conference paper

DOI: 10.1007/978-3-540-68125-0_30

Part of the Lecture Notes in Computer Science book series (LNCS, volume 5012)
Cite this paper as:
Sugiyama M., Idé T., Nakajima S., Sese J. (2008) Semi-Supervised Local Fisher Discriminant Analysis for Dimensionality Reduction. In: Washio T., Suzuki E., Ting K.M., Inokuchi A. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2008. Lecture Notes in Computer Science, vol 5012. Springer, Berlin, Heidelberg

Abstract

When only a small number of labeled samples are available, supervised dimensionality reduction methods tend to perform poorly due to overfitting. In such cases, unlabeled samples could be useful in improving the performance. In this paper, we propose a semi-supervised dimensionality reduction method which preserves the global structure of unlabeled samples in addition to separating labeled samples in different classes from each other. The proposed method has an analytic form of the globally optimal solution and it can be computed based on eigendecompositions. Therefore, the proposed method is computationally reliable and efficient. We show the effectiveness of the proposed method through extensive simulations with benchmark data sets.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Masashi Sugiyama
    • 1
  • Tsuyoshi Idé
    • 2
  • Shinichi Nakajima
    • 3
  • Jun Sese
    • 4
  1. 1.Tokyo Institute of TechnologyTokyoJapan
  2. 2.IBM ResearchKanagawaJapan
  3. 3.Nikon CorporationSaitamaJapan
  4. 4.Ochanomizu UniversityTokyoJapan

Personalised recommendations