Hsic Attribution Method #119
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
fel-thomas
requested review from
thib-s,
paulnovello,
lucashervier and
AntoninPoche
AntoninPoche
requested changes
Nov 28, 2022
xplique/attributions/global_sensitivity_analysis/hsic_attribution_method.py
Show resolved
Hide resolved
xplique/attributions/global_sensitivity_analysis/hsic_attribution_method.py
Outdated
Show resolved
Hide resolved
fel-thomas
force-pushed
the
hsic
branch
2 times, most recently
from
25bf6b3
to
14a5b6d
Compare
AntoninPoche
approved these changes
Nov 29, 2022
Co-authored-by: Paul Novello <pnovellop@gmail.com>
Co-authored-by: Paul Novello <pnovellop@gmail.com>
Co-authored-by: Paul Novello <pnovellop@gmail.com>
This was referenced Dec 14, 2022
Merged
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Outdated suggestions cannot be applied.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.
Summary
This PR introduce the work from Novello, Fel, Vigouroux
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure https://arxiv.org/abs/2206.06219 (NeurIPS 2022).
This new black-box attribution method will be part of the GSA module.
To introduce HSIC, we need 3 key ingredients: samplers, kernels and HSIC Estimator. We do that in 3 separate commits and then introduce the Attribution method by exposing the
HSICAttributionMethodAPI.HSIC Attribution method
42e2602 introduce the samplers, c56e9b3 the kernels and 8eeab03 use them to estimate HSIC.
c9a9e0f modify the abstract
GSAAttributionMethodclass to naturally derive HSIC in the next commit 4be2fa2.