Open gsarti opened 2 years ago
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!
π 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.π¬ How To Reproduce
discretized_integrated_gradients
method.Code sample
Environment
π Expected behavior
Same as #110
π Additional context
The problem is most likely due to a faulty scaling of the gradients in the
_attribute
method of theDiscretizedIntegratedGradients
class.