<ul><li>Pretext Invariant Representation Learning (PIRL) followed by Supervised Fine-Tuning (SFT) has become a standard paradigm for learning with limited labels.</li><li>The Positive Unlabeled (PU) setting involves a small set of labeled positives and a large unlabeled pool containing both positives and negatives.</li><li>The Positive Unlabeled Contrastive Learning (puCL) objective integrates weak supervision from labeled positives into the contrastive loss, without access to the class prior.</li><li>When the class prior is known, Positive Unlabeled InfoNCE (puNCE) re-weights unlabeled samples as soft positive negative mixtures for better representation learning.</li></ul>

Understanding Contrastive Representation Learning from Positive Unlabeled (PU) Data

Discover more