Skip to yearly menu bar Skip to main content


Active Learning from Imperfect Labelers

Songbai Yan · Kamalika Chaudhuri · Tara Javidi

Area 5+6+7+8 #112

Keywords: [ Active Learning ] [ Learning Theory ] [ Information Theory ]


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.

Live content is unavailable. Log in and register to view live content