2 papers
cs.LG2026
C-Score: Beyond Accuracy for Robustness Assessment in Semi-Supervised Learning under Open-World Unlabeled Contamination
Tsao-Lun Chen, Chi-Cheng Fu, Han-Yi E. Chou +1
Pseudo-label-based semi-supervised learning has achieved strong performance due to its simplicity and scalability. However, it is typically developed under a closed-world assumptio…
cs.LG2026
USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning
Tsao-Lun Chen, Chien-Liang Liu, Tzu-Ming Harry Hsu +4
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…