About the gradient flow in contrastive learning

[Gavinwxy]

I notice that you do not apply detach operation when you do contrastive learning, which means the loss gradient applies on both query and keys. I was wondering if this is a common practice because in other works based on contrastive learning, the gradients only flow through query samples. Does it make any difference on training? Any hints will be appreciated.

[lorenmt]

https://github.com/lorenmt/reco/blob/71c1b7324fd36049c6657b122ba3fef373877b72/module_list.py#L112 No gradients were flowed through keys.

[Gavinwxy]

Thanks for the reply