Active Learning from Imperfect Labelers
Abstract
We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly natural assumptions on the noise and abstention rate of the labeler. This algorithm is adaptive in a sense that it can automatically request less queries with a more informed or less noisy labeler. We couple our algorithm with lower bounds to show that under some technical conditions, it achieves nearly optimal query complexity.
Cite
Text
Yan et al. "Active Learning from Imperfect Labelers." Neural Information Processing Systems, 2016.Markdown
[Yan et al. "Active Learning from Imperfect Labelers." Neural Information Processing Systems, 2016.](https://mlanthology.org/neurips/2016/yan2016neurips-active/)BibTeX
@inproceedings{yan2016neurips-active,
title = {{Active Learning from Imperfect Labelers}},
author = {Yan, Songbai and Chaudhuri, Kamalika and Javidi, Tara},
booktitle = {Neural Information Processing Systems},
year = {2016},
pages = {2128-2136},
url = {https://mlanthology.org/neurips/2016/yan2016neurips-active/}
}