Highlights d Contrastive learning uses unlabeled data to learn representations d A new contrastive learning framework is proposed for metadata pair selection d We show its application in medical heart and lung sound data and metadata d The contrastive learning strategy only needs 10% of labeled training data
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.