← Search

Qiaozhen Zhang

2 accepted papers

2024

Mitigating Underfitting in Learning to Defer with Consistent Losses

AISTATS 2024poster

Learning to defer (L2D) allows the classifier to defer its prediction to an expert for safer predictions, by balancing the system’s accuracy and extra costs incurred by consulting the expert. Various loss functions have been proposed for L2D, but they were shown to cause the underfitting of trained…

Cited by 8SourcePDFScholar
2023

Consistent Complementary-Label Learning via Order-Preserving Losses

AISTATS 2023poster

In contrast to ordinary supervised classification tasks that require massive data with high-quality labels, complementary-label learning (CLL) deals with the weakly-supervised learning scenario where each instance is equipped with a complementary label, which specifies a class the instance does not…

Cited by 17SourcePDFScholar