Sample network sequences, not individual sequences #15
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
|
This looks good to me! Thanks for taking care of it! |
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Outdated suggestions cannot be applied.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.
Made the sampling changes discussed in #13
This is most easily seen by changes to the
utils/xai_utils.pyfile (it'd be useful to know if that works as expected with your workflows). Practically, we're only considering realistic baselines now.Notably, this approach is not good for estimating importance for static variables because a different static variable is never sampled (this is written about at the bottom of the updated
ipynb). Everything else holds, consistency within/across runs and consistency with spatiotemporal permutation experiments. Also consistent with dynamic feature permutation experiments.