Explaining Machine Learning Models using Entropic Variable Projection

TL;DR

This paper introduces a novel, model-agnostic explainability framework using entropic projections to interpret how input variables influence machine learning model predictions, applicable to various models and datasets.

Contribution

It presents the first unified formalism based on information theory for explaining input variable impacts on predictions, scalable to large datasets and different model types.

Findings

Framework is model-agnostic and scalable.

Provides convergence rates for entropic projections.

Demonstrates effectiveness on diverse datasets and models.

Abstract

In this paper, we present a new explainability formalism designed to shed light on how each input variable of a test set impacts the predictions of machine learning models. Hence, we propose a group explainability formalism for trained machine learning decision rules, based on their response to the variability of the input variables distribution. In order to emphasize the impact of each input variable, this formalism uses an information theory framework that quantifies the influence of all input-output observations based on entropic projections. This is thus the first unified and model agnostic formalism enabling data scientists to interpret the dependence between the input variables, their impact on the prediction errors, and their influence on the output predictions. Convergence rates of the entropic projections are provided in the large sample case. Most importantly, we prove that computing an explanation in our framework has a low algorithmic complexity, making it scalable to real-life large datasets. We illustrate our strategy by explaining complex decision rules learned by using XGBoost, Random Forest or Deep Neural Network classifiers on various datasets such as Adult Income, MNIST, CelebA, Boston Housing, Iris, as well as synthetic ones. We finally make clear its differences with the explainability strategies LIME and SHAP, that are based on single observations. Results can be reproduced by using the freely distributed Python toolbox https://gems-ai.aniti.fr/.