J. Ramírez Ayerbe, A. Lodi

In this work, we consider the problem of generating a set of counterfactual explanations for a group of instances, with the one-for-many allocation rule, where one explanation is allocated to a subgroup of the instances. For the first time, we solve the problem of minimizing the number of counterfactual explanations needed to explain all the instances, while considering sparsity by limiting the number of features allowed to be changed collectively in each explanation. A novel column generation framework is developed to efficiently search for the explanations. Our framework can be applied to any black-box classifier that allows an MIP representation, like neural networks with ReLU activation. Compared with a simple adaptation of a mixed-integer programming formulation from the literature, the column generation framework dominates in terms of scalability, computational performance, and quality of the solutions.

Keywords: Counterfactual Explanations, Explainability, Column Generation

Scheduled

Ramiro Melendreras Awards
June 10, 2025  5:10 PM
Sala VIP Jaume Morera i Galícia


Other papers in the same session

Semilocal Lipschitz stability in linear optimization

J. Camacho Moro, M. J. Cánovas Cánovas, H. Gfrerer, M. A. López Cerdá, J. E. Martínez Legáz, J. Parra López


Cookie policy

We use cookies in order to be able to identify and authenticate you on the website. They are necessary for the correct functioning of it, and therefore they can not be disabled. If you continue browsing the website, you are agreeing with their acceptance, as well as our Privacy Policy.

Additionally, we use Google Analytics in order to analyze the website traffic. They also use cookies and you can accept or refuse them with the buttons below.

You can read more details about our Cookie Policy and our Privacy Policy.