Code and Data for "Null importance: Disentangling relevance for interpretable machine learning."
Year: 2026
Type: dataset
Abstract: The code here mirrors that in our GitHub repository (https://github.com/krisrs1128/null_importance). Each case study is a subdirectory of the case_studies folder. The READMEs describe the commands that are used to replicate the analysis and visualization. Under case studies, the environment.yml file defines the conda environment "interpretability_case_studies" which describes all the all the necessary packages to replicate the results.The real and simulated data used as inputs for these case studies are further subdirectories, e.g., sweep_tabular/data. The experiments are run using Hydra, and the associated configuration files are stored under conf/. The CSV files used in all the figures and the figures themselves are stored under results
Source: Figshare
Authors: Kris Sankaran, Garvesh Raskutti
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7213419636
Cites:
Cited by:
Related to: