Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.09473 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929244132605952 |
|---|---|
| author | Lodi, Andrea Ramírez-Ayerbe, Jasone |
| author_facet | Lodi, Andrea Ramírez-Ayerbe, Jasone |
| contents | In this paper, 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 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, like neural networks. 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09473 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One-for-many Counterfactual Explanations by Column Generation Lodi, Andrea Ramírez-Ayerbe, Jasone Machine Learning In this paper, 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 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, like neural networks. 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. |
| title | One-for-many Counterfactual Explanations by Column Generation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.09473 |