7 papers
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…
Risk-Consistent Multiclass Learning from Random Label-Subset Membership Queries
Jiaxu Su, Junpeng Li, Changchun Hua +1
Obtaining accurate class labels is often costly or unreliable, and may also be limited by privacy or other practical conditions. Compared with asking an annotator to provide the ex…
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…
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…
A Unified Empirical Risk Minimization Framework for Flexible N-Tuples Weak Supervision
Shuying Huang, Junpeng Li, Changchun Hua +1
To alleviate the annotation burden in supervised learning, N-tuples learning has recently emerged as a powerful weakly-supervised method. While existing N-tuples learning approache…
Structure-Preserving Margin Distribution Learning for High-Order Tensor Data with Low-Rank Decomposition
Yang Xu, Junpeng Li, Changchun Hua +1
The Large Margin Distribution Machine (LMDM) is a recent advancement in classifier design that optimizes not just the minimum margin (as in SVM) but the entire margin distribution,…