USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning

Tsao-Lun Chen, Chienliang Liu, Tzu-Ming Harry Hsu, Tai-Hsien Wu, Han-Yi E. CHOU, Shun-Feng Su

Keywords: Semi-supervised learning, Unlabeled data quality, Out-of-distribution detection, Robust Semi-supervised learning, entropy-based filtering

TL;DR: We introduce USE, an entropy-based and algorithm-agnostic mechanism for unlabeled data quality control that enhances semi-supervised learning beyond heuristic OOD filtering

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, removing uninformative or harmful unlabeled data before SSL training begins. Through extensive experiments on imaging (CIFAR-100) and NLP (Yelp Review) data, it is evident that USE consistently improves accuracy and robustness under varying levels of OOD contamination. Thus, it can be concluded that the proposed approach reframes unlabeled data quality control as a structural assessment problem, and considers it as a necessary component for reliable and efficient SSL in realistic mixed-distribution environments.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 15680