A Bayesian explanation of machine learning models based on modes and functional ANOVA
Abstract
Most methods in explainable AI (XAI) focus on providing reasons for the prediction of a given set of features. However, we solve an inverse explanation problem, i.e., given the deviation of a label, find the reasons of this deviation. We use a Bayesian framework to recover the ``true'' features, conditioned on the observed label value. We efficiently explain the deviation of a label value from the mode, by identifying and ranking the influential features using the ``distances'' in the ANOVA functional decomposition. We show that the new method is more human-intuitive and robust than methods based on mean values, e.g., SHapley Additive exPlanations (SHAP values). The extra costs of solving a Bayesian inverse problem are dimension-independent.
Cite
@article{arxiv.2411.02746,
title = {A Bayesian explanation of machine learning models based on modes and functional ANOVA},
author = {Quan Long},
journal= {arXiv preprint arXiv:2411.02746},
year = {2024}
}