r74229158/xtrain_repo: ICML 2026 submission version

Zenodo (CERN European Organization for Nuclear Research) 2026 Open access

Read full text
Authors: r74229158
DOI: 10.5281/zenodo.17676967
Cited by: 0

Abstract

This release contains the code used for the ICML submission "XtrAIn: Capturing Causal Effects During Training Updates to Calculate Feature Importance in Deep Neural Networks". Changes since v1.0: Debugging dowloading data errors, Cleaner code for testing, Added testing ground.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
29 January 2026