# Covered Information Disentanglement: Model Transparency via Unbiased Permutation Importance

arXiv: https://arxiv.org/abs/2111.09744 · HTML: https://mlsanity.com/paper/2111.09744/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 18 Nov 2021.

## Builds on (most cited first, 7 of 7)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Local Rule-Based Explanations of Black Box Decision Systems](https://mlsanity.com/paper/1805.10820/) (2018)
- [Programs as Black-Box Explanations](https://mlsanity.com/paper/1611.07579/) (2016)
- [The Partial Entropy Decomposition: Decomposing multivariate entropy and mutual information via pointwise common surprisal](https://mlsanity.com/paper/1702.01591/) (2017)
- [Graph Space Embedding](https://mlsanity.com/paper/1907.13443/) (2019)

## Built on by (most cited first, 2 of 2)

- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Causal Discovery with Inverted Self-attention for Multivariate Time Series](https://mlsanity.com/paper/2607.28212/) (2026)

## Abstract (arXiv)

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 method 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.