Better Optimization can Reduce Sample Complexity: Active Semi-Supervised Learning via Convergence Rate Control

Seo Taek Kong, Soomin Jeon, Jaewon Lee, Hong-Seok Lee, Kyu-Hwan Jung

Keywords: Active Learning, Semi-Supervised Learning, Neural Tangent Kernel, Deep Learning

Abstract: Reducing the sample complexity associated with deep learning (DL) remains one of the most important problems in both theory and practice since its advent. Semi-supervised learning (SSL) tackles this task by leveraging unlabeled instances which are usually more accessible than their labeled counterparts. Active learning (AL) directly seeks to reduce the sample complexity by training a classification network and querying unlabeled instances to be annotated by a human-in-the-loop. Under relatively strict settings, it has been shown that both SSL and AL can theoretically achieve the same performance of fully-supervised learning (SL) using far less labeled samples. While empirical works have shown that SSL can attain this benefit in practice, DL-based AL algorithms have yet to show their success to the extent achieved by SSL. Given the accessible pool of unlabeled instances in pool-based AL, we argue that the annotation efficiency brought by AL algorithms that seek diversity on labeled samples can be improved upon when using SSL as the training scheme. Equipped with a few theoretical insights, we designed an AL algorithm that rather focuses on controlling the convergence rate of a classification network by actively querying instances to improve the rate of convergence upon inclusion to the labeled set. We name this AL scheme convergence rate control (CRC), and our experiments show that a deep neural network trained using a combination of CRC and a recently proposed SSL algorithm can quickly achieve high performance using far less labeled samples than SL. In contrast to a few works combining independently developed AL and SSL (ASSL) algorithms, our method is a natural fit to ASSL, and we hope our work can catalyze research combining AL and SSL as opposed to an exclusion of either.

One-sentence Summary: We propose a new active learning algorithm inspired by neural tangent kernels and demonstrate its effectiveness when combined with semi-supervised learning.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=24Nsk8Wdwd