Making Binary Classification From Multiple Unlabeled Datasets Almost Free of Supervision
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-14
DOI: 10.1109/tpami.2026.3748555 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Yuhao Wu und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Training a classifier exploiting a huge amount of supervised data is expensive or even prohibited in a situation, where the labeling cost is high. The remarkable progress in working with weaker forms of supervision is binary classification from multiple unlabeled datasets which requires the knowledge of exact class priors for all unlabeled datasets. However, the availability of class priors is restrictive in many real-world scenarios. To address this issue, we propose to solve a new problem setting, i.e., binary classification from multiple unlabeled datasets with only one pairwise numerical relationship of class priors (MU-OPPO), which knows the relative order (which unlabeled dataset has a higher proportion of positive examples) of two class-prior probabilities for two datasets among multiple unlabeled datasets. In MU-OPPO, we do not need the class priors for all unlabeled datasets, but we only require that there exists a pair of unlabeled datasets for which we know which unlabeled dataset has a larger class prior. Clearly, this form of supervision is easier to be obtained, which can make labeling costs almost free. We propose a novel framework to handle the MU-OPPO problem, which consists of four sequential modules: (i) pseudo label assignment; (ii) confident example collection; (iii) class prior estimation; (iv) classifier training with estimated class priors. Theoretically, we analyze the gap between estimated class priors and true class priors under the proposed framework. Empirically, we confirm the superiority of our framework with comprehensive experiments. Experimental results demonstrate that our framework brings smaller estimation errors of class priors and better performance of binary classification. The code is available at: https://github.com/wu-yu-hao/MU-OPPO.
Zitieren
APA
Wu, Y., Xia, X., Yu, J., Han, B., Niu, G., Sugiyama, M., & Liu, T. (2026). Making Binary Classification From Multiple Unlabeled Datasets Almost Free of Supervision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-14. https://doi.org/10.1109/tpami.2026.3748555
Vancouver
Wu Y, Xia X, Yu J, Han B, Niu G, Sugiyama M, et al. Making Binary Classification From Multiple Unlabeled Datasets Almost Free of Supervision. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-14. doi:10.1109/tpami.2026.3748555
BibTeX
@article{Wu2026,
author = {Wu, Yuhao and Xia, Xiaobo and Yu, Jun and Han, Bo and Niu, Gang and Sugiyama, Masashi and Liu, Tongliang},
title = {Making Binary Classification From Multiple Unlabeled Datasets Almost Free of Supervision},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
pages = {1--14},
doi = {10.1109/tpami.2026.3748555}
}
EUVIMED