Positive Unlabeled Contrastive Learning

arXiv:2206.01206v3 Announce Type: replace
Abstract: Self-supervised pretraining on unlabeled data followed by supervised fine-tuning on labeled data is a popular paradigm for learning from limited labeled examples. We extend this paradigm to the classical positive unlabeled (PU) setting, where the task is to learn a binary classifier given only a few labeled positive samples, and (often) a large amount of unlabeled samples (which could be positive or negative).
We first propose a simple extension of standard infoNCE family of contrastive …

abstract arxiv binary classifier cs.ai cs.lg data examples fine-tuning learn paradigm popular positive pretraining samples supervised fine-tuning type