Large sets of unlabelled data within the healthcare domain remain underutilized. Active learning offers a way to exploit these datasets by iteratively requesting an oracle (e.g. medical professional) to label instances. This process, which can be costly and time-consuming is overly-dependent upon an oracle. To alleviate this burden, we propose SoQal, a questioning strategy that dynamically determines when a label should be requested from an oracle. We perform experiments on five publically-available datasets and illustrate SoQal's superiority relative to baseline approaches, including its ability to reduce oracle label requests by up to 35%. SoQal also performs competitively in the presence of label noise: a scenario that simulates clinicians' uncertain diagnoses when faced with difficult classification tasks.
@article{arxiv.2004.10468,
title = {SoQal: Selective Oracle Questioning in Active Learning},
author = {Dani Kiyasseh and Tingting Zhu and David A. Clifton},
journal= {arXiv preprint arXiv:2004.10468},
year = {2020}
}