Semi-Supervised Learning from a Translation Model Between Data Distributions
Abstract
In this paper, we introduce a probabilistic classification model to address the task of semi-supervised learning. The major novelty of our proposal stems from measuring distributional relationships between the labeled and unlabeled data. This is achieved from a stochastic translation model between data distributions that is estimated from a mixture model. The proposed classifier is defined from the combination of both the translation model and a kernel logistic regression on labeled data. Experimental results obtained over synthetic and real-world data sets validate the usefulness of our proposal.
Cite
Text
Anaya-Sánchez et al. "Semi-Supervised Learning from a Translation Model Between Data Distributions." International Joint Conference on Artificial Intelligence, 2011. doi:10.5591/978-1-57735-516-8/IJCAI11-199Markdown
[Anaya-Sánchez et al. "Semi-Supervised Learning from a Translation Model Between Data Distributions." International Joint Conference on Artificial Intelligence, 2011.](https://mlanthology.org/ijcai/2011/anayasanchez2011ijcai-semi/) doi:10.5591/978-1-57735-516-8/IJCAI11-199BibTeX
@inproceedings{anayasanchez2011ijcai-semi,
title = {{Semi-Supervised Learning from a Translation Model Between Data Distributions}},
author = {Anaya-Sánchez, Henry and Sotoca, José Martínez and Usó, Adolfo Martínez},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2011},
pages = {1165-1170},
doi = {10.5591/978-1-57735-516-8/IJCAI11-199},
url = {https://mlanthology.org/ijcai/2011/anayasanchez2011ijcai-semi/}
}