Bayesian Active Learning With Abstention Feedbacks
This addresses the problem of efficient labeling in machine learning for scenarios with unreliable or abstaining labelers, representing an incremental improvement in active learning methods.
The paper tackles pool-based active learning with abstention feedbacks, where labelers can abstain from labeling queries at an unknown rate, by developing two Bayesian greedy algorithms that simultaneously learn classification and abstention rates, achieving near-optimal guarantees with a (1-1/e) constant factor approximation.
We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the classification problem and the unknown abstention rate at the same time. These are achieved by simply incorporating the estimated average abstention rate into the greedy criteria. We prove that both algorithms have near-optimality guarantees: they respectively achieve a ${(1-\frac{1}{e})}$ constant factor approximation of the optimal expected or worst-case value of a useful utility function. Our experiments show the algorithms perform well in various practical scenarios.