Exploiting Ontology Structures and Unlabeled Data for Learning

Abstract

We present and analyze a theoretical model designed to understand and explain the effectiveness of ontologies for learning multiple related tasks from primarily unlabeled data. We present both information-theoretic results as well as efficient algorithms. We show in this model that an ontology, which specifies the relationships between multiple outputs, in some cases is sufficient to completely learn a classification using a large unlabeled data source.

Cite

Text

Balcan et al. "Exploiting Ontology Structures and Unlabeled Data for Learning." International Conference on Machine Learning, 2013.

Markdown

[Balcan et al. "Exploiting Ontology Structures and Unlabeled Data for Learning." International Conference on Machine Learning, 2013.](https://mlanthology.org/icml/2013/balcan2013icml-exploiting/)

BibTeX

@inproceedings{balcan2013icml-exploiting,
  title     = {{Exploiting Ontology Structures and Unlabeled Data for Learning}},
  author    = {Balcan, Nina and Blum, Avrim and Mansour, Yishay},
  booktitle = {International Conference on Machine Learning},
  year      = {2013},
  pages     = {1112-1120},
  volume    = {28},
  url       = {https://mlanthology.org/icml/2013/balcan2013icml-exploiting/}
}