Principled Diverse Counterfactuals in Multilinear Models
This addresses the challenge of model interpretability and fairness in ML applications, which is crucial for ensuring trust and compliance in automated systems.
The paper tackles the problem of verifying black-box ML models by proposing a method to generate diverse counterfactual explanations for multilinear models, such as Random Forests and Bayesian Networks, to ensure decisions are based on proper criteria and avoid discrimination.
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.