Open Access

ARTICLE

Iterative Semi-Supervised Learning Using Softmax Probability

Heewon Chung, Jinseok Lee^*

Department of Biomedical Engineering, College of Electronics and Information, Kyung Hee University, Yongin-si, Gyeonggi-do, 17104, Korea

* Corresponding Author: Jinseok Lee. Email:

Computers, Materials & Continua 2022, 72(3), 5607-5628. https://doi.org/10.32604/cmc.2022.028154

Received 03 February 2022; Accepted 10 March 2022; Issue published 21 April 2022

Abstract

For the classification problem in practice, one of the challenging issues is to obtain enough labeled data for training. Moreover, even if such labeled data has been sufficiently accumulated, most datasets often exhibit long-tailed distribution with heavy class imbalance, which results in a biased model towards a majority class. To alleviate such class imbalance, semi-supervised learning methods using additional unlabeled data have been considered. However, as a matter of course, the accuracy is much lower than that from supervised learning. In this study, under the assumption that additional unlabeled data is available, we propose the iterative semi-supervised learning algorithms, which iteratively correct the labeling of the extra unlabeled data based on softmax probabilities. The results show that the proposed algorithms provide the accuracy as high as that from the supervised learning. To validate the proposed algorithms, we tested on the two scenarios: with the balanced unlabeled dataset and with the imbalanced unlabeled dataset. Under both scenarios, our proposed semi-supervised learning algorithms provided higher accuracy than previous state-of-the-arts. Code is available at .

---

Keywords

---