-
Notifications
You must be signed in to change notification settings - Fork 50
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Hsic Attribution Method #119
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I do not understand the HSIC method in depth so I cannot detect if the implementation is right. However, I made some comments on the form.
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Outdated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
25bf6b3
to
14a5b6d
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
seems good to me
Co-authored-by: Paul Novello <pnovellop@gmail.com>
Co-authored-by: Paul Novello <pnovellop@gmail.com>
Co-authored-by: Paul Novello <pnovellop@gmail.com>
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
HSICAttributionMethod
API.HSIC Attribution method
42e2602 introduce the samplers, c56e9b3 the kernels and 8eeab03 use them to estimate HSIC.
c9a9e0f modify the abstract
GSAAttributionMethod
class to naturally derive HSIC in the next commit 4be2fa2.