Add FSI and STI approximation methods #7
Merged
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Outdated suggestions cannot be applied.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.
New Methods
This PR adds two new approximation methods for two different indices.
FSI Regression Estimator
The regression estimator is only available for the Faithful Shapley Index (FSI). It functions like KernelSHAP for the Shapley values but adds each interaction up to a certain order as an individual player (feature) in the least squares representation of the Shapley value.
STI Permutation Estimator
The Shapley Taylor Index (STI) can be estimated similarly to the Shapley Interaction Index (SII) with permutation sampling. However, it requires far more evaluations of the underlying game function, since it needs to exhaustively evaluate all lower order interactions.