3 papers
cs.LG2026
A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees
Miao Zhang, Junpeng Li, Changchun Hua +1
Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire. However, many…
cs.LG2025
Learning from N-Tuple Data with M Positive Instances: Unbiased Risk Estimation and Theoretical Guarantees
Miao Zhang, Junpeng Li, ChangChun HUa +1
Weakly supervised learning often operates with coarse aggregate signals rather than instance labels. We study a setting where each training example is an -tuple containing exact…
cs.LG2025
Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
Miao Zhang, Junpeng Li, Changchun Hua +1
Positive--Unlabeled (PU) learning considers settings in which only positive and unlabeled data are available, while negatives are missing or left unlabeled. This situation is commo…