Search Machine Learning Repository:
Exploiting Ontology Structures and Unlabeled Data for Learning
Authors: Avrim Blum, Yishay Mansour and Maria-Florina Balcan
Conference: Proceedings of the 30th International Conference on Machine Learning (ICML-13)
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.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).