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.

Sign up for GitHub

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

Jump to bottom

Integrated Gradients - Higher Convergence Delta with more Steps? #1334

Open

Steven-Palayew opened this issue Aug 25, 2024 · 0 comments

Steven-Palayew commented Aug 25, 2024

Working with the example from this tutorial here: https://github.com/munnm/XAI-for-practitioners/blob/462b1fc79d9cf7998992e1878c60d9d4c6282982/05-text/layer_integrated_gradients.ipynb, it seems as though using less steps actually decreases the size of the convergence delta? Ie see screenshots below.

I'm just wondering if this is normal behaviour? From #311 it seems like we would expect the opposite to occur.

TIA!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment