Positive Unlabeled Contrastive Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929294619443200 |
|---|---|
| author | Acharya, Anish Sanghavi, Sujay Jing, Li Bhushanam, Bhargav Choudhary, Dhruv Rabbat, Michael Dhillon, Inderjit |
| author_facet | Acharya, Anish Sanghavi, Sujay Jing, Li Bhushanam, Bhargav Choudhary, Dhruv Rabbat, Michael Dhillon, Inderjit |
| contents | 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 losses, to the PU setting; and show that this learns superior representations, as compared to existing unsupervised and supervised approaches. We then develop a simple methodology to pseudo-label the unlabeled samples using a new PU-specific clustering scheme; these pseudo-labels can then be used to train the final (positive vs. negative) classifier. Our method handily outperforms state-of-the-art PU methods over several standard PU benchmark datasets, while not requiring a-priori knowledge of any class prior (which is a common assumption in other PU methods). We also provide a simple theoretical analysis that motivates our methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2206_01206 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Positive Unlabeled Contrastive Learning Acharya, Anish Sanghavi, Sujay Jing, Li Bhushanam, Bhargav Choudhary, Dhruv Rabbat, Michael Dhillon, Inderjit Machine Learning Artificial Intelligence 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 losses, to the PU setting; and show that this learns superior representations, as compared to existing unsupervised and supervised approaches. We then develop a simple methodology to pseudo-label the unlabeled samples using a new PU-specific clustering scheme; these pseudo-labels can then be used to train the final (positive vs. negative) classifier. Our method handily outperforms state-of-the-art PU methods over several standard PU benchmark datasets, while not requiring a-priori knowledge of any class prior (which is a common assumption in other PU methods). We also provide a simple theoretical analysis that motivates our methods. |
| title | Positive Unlabeled Contrastive Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2206.01206 |