← Search

Olivier HUMBERT

2 accepted papers

2023

Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.

ICML 2023oral

Semi-supervised learning is a powerful technique for leveraging unlabeled data to improve machine learning models, but it can be affected by the presence of ``informative" labels, which occur when some classes are more likely to be labeled than others. In the missing data literature, such labels are…

Cited by 10SourcePDFScholar
2023

Don’t fear the unlabelled: safe semi-supervised learning via debiasing

ICLR 2023poster

Semi-supervised learning (SSL) provides an effective means of leveraging unlabelled data to improve a model’s performance. Even though the domain has received a considerable amount of attention in the past years, most methods present the common drawback of lacking theoretical guarantees. Our startin…