-
Notifications
You must be signed in to change notification settings - Fork 36
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鈥檒l occasionally send you account related emails.
Already on GitHub? Sign in to your account
Inconsistent batching for DiscretizedIntegratedGradients attributions #113
Labels
Comments
Hi @soumyasanyal, FYI our library supports your method Discretized IG for feature attribution, but at the moment we are experiencing some issues with consistency across single-example and batched attribution (i.e. there is some issue with the creation of orthogonal approximation steps for a batch, see also #114 for additional info). It would be great if you could have a look! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
馃悰 Bug Report
Despite fixing batched attribution so that results are consistent with individual attribution (see #110), the method
DiscretizedIntegratedGradients
still produces different results when applied to a batch of examples.馃敩 How To Reproduce
discretized_integrated_gradients
method.Code sample
Environment
馃搱 Expected behavior
Same as #110
馃搸 Additional context
The problem is most likely due to a faulty scaling of the gradients in the
_attribute
method of theDiscretizedIntegratedGradients
class.The text was updated successfully, but these errors were encountered: