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.
Palabras clave: Counterfactual Explanations, Explainability, Column Generation
Programado
Premio Ramiro Melendreras
10 de junio de 2025 17:10
Sala VIP Jaume Morera i Galícia