2020/03/04 by Christopher Tosh, Akshay Krishnamurthy, Tosh, Christopher +3 · 1 citation
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Text and Document Classification Technologies #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2003.02234
openalex publication_date 2020/03/04 · openalex created_date 2020/03/13 · openalex updated_date 2026/07/28
Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling assumptions, we prove that contrastive learning is capable of recovering a representation of documents that reveals their underlying topic posterior information to linear models. We apply this procedure in a semi-supervised setup and demonstrate empirically that linear classifiers with these representations perform well in document classification tasks with very few training examples.