Contrastive Learning

Contrastive learning is a machine learning technique that trains models to produce vector embeddings by maximising similarity between representations of the same or augmented instance (positive pairs) while minimising similarity between representations of different instances (negative pairs). It enables models to learn meaningful feature representations without requiring large amounts of labelled training data. In accessibility and testing contexts, contrastive learning has been applied to learn embeddings of HTML DOM structures, enabling automated tools to distinguish functionally distinct web pages from near-duplicate ones.