Covered Information Disentanglement: Model Transparency via Unbiased Permutation Importance

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)

Abstract

Model transparency is a prerequisite in many domains and an increasingly popular area in machine learning research. In the medical domain, for instance, unveiling the mechanisms behind a disease often has higher priority than the diagnostic itself since it might dictate or guide potential treatments and research directions. One of the most popular approaches to explain model global predictions is the permutation importance where the performance on permuted data is benchmarked against the baseline. However, this method and other related approaches will undervalue the importance of a feature in the presence of covariates since these cover part of its provided information. To address this issue, we propose Covered Information Disentanglement (CID), a framework that considers all feature information overlap to correct the values provided by permutation importance. We further show how to compute CID efficiently when coupled with Markov random fields. We demonstrate its efficacy in adjusting permutation importance first on a controlled toy dataset and discuss its effect on real-world medical data.
Original languageEnglish
Title of host publicationProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
PublisherAssociation for the Advancement of Artificial Intelligence
Pages7984-7992
Volume36
ISBN (Electronic)1577358767
Publication statusPublished - 30 Jun 2022
Event36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
Duration: 22 Feb 20221 Mar 2022

Publication series

NameProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022

Conference

Conference36th AAAI Conference on Artificial Intelligence, AAAI 2022
CityVirtual, Online
Period22/02/20221/03/2022

Cite this