Principled Diverse Counterfactuals in Multilinear Models

TL;DR

This paper introduces a method for generating diverse counterfactual explanations for multilinear models, including Random Forests and Bayesian Networks, to improve model interpretability and fairness verification.

Contribution

It presents a novel approach to produce diverse counterfactuals specifically tailored for multilinear models, enhancing transparency and accountability.

Findings

Effective generation of diverse counterfactuals demonstrated

Applicable to a broad class of models including Random Forests

Supports model verification and fairness assessment

Abstract

Machine learning (ML) applications have automated numerous real-life tasks, improving both private and public life. However, the black-box nature of many state-of-the-art models poses the challenge of model verification; how can one be sure that the algorithm bases its decisions on the proper criteria, or that it does not discriminate against certain minority groups? In this paper we propose a way to generate diverse counterfactual explanations from multilinear models, a broad class which includes Random Forests, as well as Bayesian Networks.