Header logo is

Semi-Supervised Learning through Principal Directions Estimation

2003

Conference Paper

ei


We describe methods for taking into account unlabeled data in the training of a kernel-based classifier, such as a Support Vector Machines (SVM). We propose two approaches utilizing unlabeled points in the vicinity of labeled ones. Both of the approaches effectively modify the metric of the pattern space, either by using non-spherical Gaussian density estimates which are determined using EM, or by modifying the kernel function using displacement vectors computed from pairs of unlabeled and labeled points. The latter is linked to techniques for training invariant SVMs. We present experimental results indicating that the proposed technique can lead to substantial improvements of classification accuracy.

Author(s): Chapelle, O. and Schölkopf, B. and Weston, J.
Journal: ICML Workshop, The Continuum from Labeled to Unlabeled Data in Machine Learning & Data Mining
Pages: 7
Year: 2003
Day: 0

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: ICML 2003 Workshop: The Continuum from Labeled to Unlabeled Data in Machine Learning & Data Mining
Event Place: Washington, DC, USA

Digital: 0
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PostScript

BibTex

@inproceedings{2168,
  title = {Semi-Supervised Learning through Principal Directions Estimation},
  author = {Chapelle, O. and Sch{\"o}lkopf, B. and Weston, J.},
  journal = {ICML Workshop, The Continuum from Labeled to Unlabeled Data in Machine Learning & Data Mining},
  pages = {7},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  year = {2003}
}