EasyDeepLearn

How does contrastive learning work?

hard

Answer

  • Create two augmented views of the same example (positive pair) and treat other examples as negatives.
  • Train an encoder so positives are close in embedding space and negatives are far, using a loss like InfoNCE.
  • Examples: SimCLR, MoCo, CLIP (contrasts image with text).
  • Produces general-purpose embeddings useful for many downstream tasks.
Check yourself — multiple choice
  • It pulls all embeddings toward a single point
  • It pulls positive pairs together and pushes negatives apart
  • It requires human labels for each pair
  • It only works with text data

Positives close, negatives far — that's the InfoNCE-style objective.

#representation-learning

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions