A mistake that often goes unnoticed.
you could retrain the two embedding models jointly by minimzing the L2 distance between the embeddings of the same input and maximizing it for different inputs.
this training can be achieved using a contrastive loss.
That's an interesting point... Thank you, AVI CHAWLA !
Would you do a dimensional reduction, say PCA before or after concatenation?
you could retrain the two embedding models jointly by minimzing the L2 distance between the embeddings of the same input and maximizing it for different inputs.
this training can be achieved using a contrastive loss.
That's an interesting point... Thank you, AVI CHAWLA !
Would you do a dimensional reduction, say PCA before or after concatenation?