We study a pool-based sequential active learning (AL), in which one sample is queried at each time from a large pool of unlabeled data according to a selection criterion. For this framework, we propose two selection criteria, named expected-kernel-discrepancy (EKD) and expected-kernel-loss (EKL), by leveraging the particular structure of multiple kernel learning (MKL). Also, it is identified that the proposed EKD and EKL successfully generalize the concepts of popular query-by-committee (QBC) and expected-model-change (EMC), respectively. Via experimental results with real-data sets, we verify the effectiveness of the proposed criteria compared with the existing methods.
@article{arxiv.2010.11421,
title = {Pool-based sequential active learning with multi kernels},
author = {Jeongmin Chae and Songnam Hong},
journal= {arXiv preprint arXiv:2010.11421},
year = {2020}
}