[2603.00404] USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning

Computer Science > Machine Learning arXiv:2603.00404 (cs) [Submitted on 28 Feb 2026] Title:USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning Authors:Tsao-Lun Chen, Chien-Liang Liu, Tzu-Ming Harry Hsu, Tai-Hsien Wu, Chi-Cheng Fu, Han-Yi E. Chou, Shun-Feng Su View a PDF of the paper titled USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning, by Tsao-Lun Chen and 6 other authors View PDF HTML (experimental) Abstract:In this study, a novel idea, Uncertainty Structure Estimation (USE), a lightweight, algorithm-agnostic procedure that emphasizes the often-overlooked role of unlabeled data quality is introduced for Semi-supervised learning (SSL). SSL has achieved impressive progress, but its reliability in deployment is limited by the quality of the unlabeled pool. In practice, unlabeled data are almost always contaminated by out-of-distribution (OOD) samples, where both near-OOD and far-OOD can negatively affect performance in different ways. We argue that the bottleneck does not lie in algorithmic design, but rather in the absence of principled mechanisms to assess and curate the quality of unlabeled data. The proposed USE trains a proxy model on the labeled set to compute entropy scores for unlabeled samples, and then derives a threshold, via statistical comparison against a reference distribution, that separates informative (structured) from uninformative (structureless) samples. This enables assessment as a preprocessing step, re...