Sample contrastive #167
Merged
Sample contrastive #167
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Previously in
ContrastiveLoss, we would take the firstn_contrastivesamples (excluding the joint index) as the contrastive samples, and rely on shuffling between batches to provide randomness. However, this still leads to correlated contrastive samples within a batch. This pull request fixes that to instead sample the contrastive samples from the remainder of the batch. For convenience, we updateMaximumLikelihoodLossto also accept a key, for consistency with the updatedContrastiveLoss.This could be a breaking change for users with a custom loss function used with
fit_to_data, which now expects the loss function to allow passing of a key, but is trivial to fix by allowing passing of a key (even if ignored).