ProxySPEX Approximator#442
Merged
mmschlk merged 12 commits intommschlk:mainfrom Oct 24, 2025
landonbutler:main
Merged
Conversation
Added ProxySPEX to sparse approximators, with additional testing and …
Owner
|
Amazing contribution! Will check it out shortly! :) |
# Conflicts: # docs/source/notebooks/language_notebooks/language_model_game.ipynb # src/shapiq/approximator/sparse/base.py
mmschlk
approved these changes
Oct 24, 2025
Owner
mmschlk
left a comment
mmschlk
left a comment
There was a problem hiding this comment.
Merged the latest changes into the branch and played around with ProxySPEX! Very cool! I will be doing some cleaning up at some point in the approximators but for now this is amazing! Nice work! ❤️
mmschlk
added
feature 💡
…er/main # Conflicts: # pyproject.toml
Contributor
|
Awesome work! Thanks to @landonbutler @mmschlk and @Advueu963 for helping make this possible. |
This file contains hidden or 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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ProxySPEX Approximator
Motivation and Context
Recently, we have introduced the ProxySPEX approximator, which can discover interactions at scale, and demonstrates an order-of-magnitude savings of the number of model inferences over the SPEX approximator. This PR includes the addition of the approximator, comprehensive testing, and examples added to both the language and vision notebooks.
Public API Changes
Added the ProxySPEX approximator as an option throughout SHAP-IQ.
How Has This Been Tested?
We have added
test_approximator_proxyspex.pywith comprehensive testing, alongside additional tests withintest_approximator_base_sparse.py.Checklist
CHANGELOG.md(if relevant for users).