Active Learning from Imperfect Labelers
Preprint
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.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Bayesian Active Learning With Non-Persistent NoiseIEEE Transactions on Information Theory, 2015
- The Geometry of Generalized Binary SearchIEEE Transactions on Information Theory, 2011
- Active Learning in the Non-realizable Case2006
- Optimal aggregation of classifiers in statistical learningThe Annals of Statistics, 2004