Abstract
Deep learning (DL) relies on massive amounts of labeled data, and improving its labeled sample-efficiency remains one of the most important problems since its advent. Semi-supervised learning (SSL) leverages unlabeled data that are more accessible than their labeled counterparts. Active learning (AL) selects unlabeled instances to be annotated by a human-in-the-loop in hopes of better performance with less labeled data. Given the accessible pool of unlabeled data in pool-based AL, it seems natural to use SSL when training and AL to update the labeled set; however, algorithms designed for their combination remain limited. In this work, we first prove that convergence of gradient descent on sufficiently wide ReLU networks can be expressed in terms of their Gram matrix' eigen-spectrum. Equipped with a few theoretical insights, we propose convergence rate control (CRC), an AL algorithm that selects unlabeled data to improve the problem conditioning upon inclusion to the labeled set, by formulating an acquisition step in terms of improving training dynamics. Extensive experiments show that SSL algorithms coupled with CRC can achieve high performance using very few labeled data.
Abstract (translated)
URL
https://arxiv.org/abs/2104.03525
