# Characterizing the contribution of dependent features in XAI methods

arXiv: https://arxiv.org/abs/2304.01717 · HTML: https://mlsanity.com/paper/2304.01717/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 4 Apr 2023.

## Builds on (most cited first, 6 of 6)

- [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)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Principles and Practice of Explainable Machine Learning](https://mlsanity.com/paper/2009.11698/) (2020)
- [Explaining black box decisions by Shapley cohort refinement](https://mlsanity.com/paper/1911.00467/) (2019)
- [What's in a GitHub Star? Understanding Repository Starring Practices in a Social Coding Platform](https://mlsanity.com/paper/1811.07643/) (2018)

## Built on by (most cited first, 4 of 4)

- [A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME](https://mlsanity.com/paper/2305.02012/) (2023)
- [Why do explanations fail? A typology and discussion on failures in XAI](https://mlsanity.com/paper/2405.13474/) (2024)
- [Explainable Artificial Intelligence and Multicollinearity : A Mini Review of Current Approaches](https://mlsanity.com/paper/2406.11524/) (2024)
- [Explainable Artificial Intelligence For The Detection and Characterisation of Stage B Heart Failure](https://mlsanity.com/paper/2606.30665/) (2026)

## Abstract (arXiv)

Explainable Artificial Intelligence (XAI) provides tools to help understanding how the machine learning models work and reach a specific outcome. It helps to increase the interpretability of models and makes the models more trustworthy and transparent. In this context, many XAI methods were proposed being SHAP and LIME the most popular. However, the proposed methods assume that used predictors in the machine learning models are independent which in general is not necessarily true. Such assumption casts shadows on the robustness of the XAI outcomes such as the list of informative predictors. Here, we propose a simple, yet useful proxy that modifies the outcome of any XAI feature ranking method allowing to account for the dependency among the predictors. The proposed approach has the advantage of being model-agnostic as well as simple to calculate the impact of each predictor in the model in presence of collinearity.