Header logo is

Semi-supervised Learning via Generalized Maximum Entropy

2010

Conference Paper

ei


Various supervised inference methods can be analyzed as convex duals of the generalized maximum entropy (MaxEnt) framework. Generalized MaxEnt aims to find a distribution that maximizes an entropy function while respecting prior information represented as potential functions in miscellaneous forms of constraints and/or penalties. We extend this framework to semi-supervised learning by incorporating unlabeled data via modifications to these potential functions reflecting structural assumptions on the data geometry. The proposed approach leads to a family of discriminative semi-supervised algorithms, that are convex, scalable, inherently multi-class, easy to implement, and that can be kernelized naturally. Experimental evaluation of special cases shows the competitiveness of our methodology.

Author(s): Erkan, AN. and Altun, Y.
Book Title: JMLR Workshop and Conference Proceedings Volume 9: AISTATS 2010
Journal: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010)
Pages: 209-216
Year: 2010
Month: May
Day: 0
Editors: Teh, Y.W. , M. Titterington
Publisher: JMLR

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

Event Name: Thirteenth International Conference on Artificial Intelligence and Statistics
Event Place: Chia Laguna Resort, Italy

Address: Cambridge, MA, USA
Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{6622,
  title = {Semi-supervised Learning via Generalized Maximum Entropy},
  author = {Erkan, AN. and Altun, Y.},
  journal = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010)},
  booktitle = {JMLR Workshop and Conference Proceedings Volume 9: AISTATS 2010},
  pages = {209-216},
  editors = {Teh, Y.W. , M. Titterington},
  publisher = {JMLR},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Cambridge, MA, USA},
  month = may,
  year = {2010},
  doi = {},
  month_numeric = {5}
}