This repository contains the source codes of using explainable artificial intelligence (XAI) techniques to analyze ElemNet. To explore the interpretability of ElemNet, the interpretation of ElemNet is conducted through both post-hoc and transparency explanations.
- Kewei Wang, Vishu Gupta, Claire Songhyun Lee, Yuwei Mao, Muhammed Nur Talha Kilic, Youjia Li, Zanhua Huang, Wei-keng Liao, Alok Choudhary, and Ankit Agrawal. XElemNet: Towards Explainable AI for Deep Neural Networks in Materials Science. （Submitted）
Here is a brief description of the codes:
- get_labels: code for generating the labels from trained ElemNet
- xelemnet: code for applying a suite of explainable AI (XAI) techniques for both post-hoc and transparency explanations to the ElemNet model
The code was developed by Kewei Wang from the CUCIS group at the Electrical and Computer Engineering Department at Northwestern University.
- Kewei Wang <keweiwang2019@u.northwestern.edu>
This work is supported in part by the following grants: NSF awards OAC-2331329, CMMI-2053929; NIST award 70NANB19H005; DOE award DE-SC0021399; and Northwestern Center for Nanocombinatorics.