Unsupervised Active Learning in Large Domains
Abstract
Active learning is a powerful approach to analyzing data effectively. We show that the feasibility of active learning depends crucially on the choice of measure with respect to which the query is being optimized. The standard information gain, for example, does not permit an accurate evaluation with a small committee, a representative subset of the model space. We propose a surrogate measure requiring only a small committee and discuss the properties of this new measure. We devise, in addition, a bootstrap approach for committee selection. The advantages of this approach are illustrated in the context of recovering (regulatory) network models.
Cite
Text
Steck and Jaakkola. "Unsupervised Active Learning in Large Domains." Conference on Uncertainty in Artificial Intelligence, 2002.Markdown
[Steck and Jaakkola. "Unsupervised Active Learning in Large Domains." Conference on Uncertainty in Artificial Intelligence, 2002.](https://mlanthology.org/uai/2002/steck2002uai-unsupervised/)BibTeX
@inproceedings{steck2002uai-unsupervised,
title = {{Unsupervised Active Learning in Large Domains}},
author = {Steck, Harald and Jaakkola, Tommi S.},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2002},
pages = {469-476},
url = {https://mlanthology.org/uai/2002/steck2002uai-unsupervised/}
}