Explaining Machine Learning Models using Entropic Variable Projection
This addresses the need for scalable, unified explanations of machine learning models for data scientists, though it appears incremental compared to existing methods like LIME and SHAP.
The paper introduces a new model-agnostic explainability formalism called Entropic Variable Projection that quantifies how input variables impact predictions across entire datasets, proving it has low algorithmic complexity for scalability on large datasets like Adult Income and MNIST.
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/.