Gaussian fields for semi-supervised regression and correspondence learning

Gaussian fields (GF) have recently received considerable attention for dimension reduction and semi-supervised classification. In this paper we show how the GF framework can be used for semi-supervised regression on high-dimensional data. We propose an active learning strategy based on entropy minimization and a maximum likelihood model selection method. Furthermore, we show how a recent generalization of the LLE algorithm for correspondence learning can be cast into the GF framework, which obviates the need to choose a representation dimensionality.

@Article{VV06,
  author       = "Jakob Verbeek and Nikos Vlassis",
  title        = "Gaussian fields for semi-supervised regression and correspondence learning",
  journal      = "Pattern Recognition",
  number       = "10",
  volume       = "39",
  pages        = "1864--1875",
  month        = "oct",
  year         = "2006",
  keywords     = "LEAR",
  url          = "http://lear.inrialpes.fr/pubs/2006/VV06"
}