none_encoded_decoded hint mode #126
Open
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
eqimp
changed the title
# for free
to join this conversation on GitHub.
Already have an account?
# 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Outdated suggestions cannot be applied.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.
This PR adds none_encoded_decoded hint usage mode, which preserves the same computation graphs to encoded_decoded mode but without computing hint losses.
On average this mode performs better than the ‘none’ hint usage mode, but the main goal of adding this mode is to provide a clearer comparison of Hints vs. No hints modes, keeping computation graphs the same.
This modification was inspired by the paper Neural Algorithmic Reasoning Without Intermediate Supervision (https://arxiv.org/abs/2306.13411), but note that the main results from this paper require additional modifications.