2000 character limit reached
One-for-many Counterfactual Explanations by Column Generation
Published 12 Feb 2024 in cs.LG and stat.ML | (2402.09473v1)
Abstract: 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.
- Machine bias: There’s software used across the country to predict future criminals. and it’s biased against blacks. 2016. URL https://www. propublica. org/article/machine-bias-risk-assessments-in-criminal-sentencing.
- On the computation of counterfactual explanations--a survey. arXiv preprint arXiv:1911.07749.
- Using neural network rule extraction and decision tables for credit-risk evaluation. Management Science, 49(3):312--329.
- Branch-and-price: Column generation for solving huge integer programs. Operations research, 46(3):316--329.
- JANOS: an integrated predictive and prescriptive modeling framework. INFORMS Journal on Computing, 34(2):807--816.
- Generating collective counterfactual explanations in score-based classification via mathematical optimization. Expert Systems with Applications, 238:121954.
- Mathematical optimization modelling for group counterfactual explanations. Forthcoming in European Journal of Operational Research.
- Cortez, P. (2014). Student Performance. UCI Machine Learning Repository. DOI: https://doi.org/10.24432/C5TG7T.
- Techniques for interpretable machine learning. Communications of the ACM, 63(1):68--77.
- UCI machine learning repository.
- Deep neural networks and mixed integer linear optimization. Constraints, 23(3):296--309.
- Guidotti, R. (2022). Counterfactual explanations and how to find them: literature review and benchmarking. Forthcoming in Data Mining and Knowledge Discovery.
- Gurobi Optimization, L. (2021). Gurobi optimizer reference manual.
- Simple rules to guide expert classifications. Journal of the Royal Statistical Society: Series A (Statistics in Society), 183(3):771--800.
- Model-agnostic counterfactual explanations for consequential decisions. In International Conference on Artificial Intelligence and Statistics, pages 895--905. PMLR.
- A survey of algorithmic recourse: contrastive explanations and consequential recommendations. ACM Computing Surveys, 55(5):1--29.
- Good counterfactuals and where to find them: A case-based technique for generating counterfactuals for explainable AI (XAI). In International Conference on Case-Based Reasoning, pages 163--178. Springer.
- Globe-ce: A translation-based approach for global counterfactual explanations. In International Conference on Machine Learning.
- Explaining data-driven document classifications. MIS Quarterly, 38(1):73--99.
- Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267:1--38.
- Interpretable machine learning--a brief history, state-of-the-art and challenges. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 417--431. Springer.
- Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 607--617.
- Optimal counterfactual explanations in tree ensembles. In International Conference on Machine Learning, pages 8422--8431. PMLR.
- Patel, K. (2023). Column generation estimator. https://github.com/krooonal/col_gen_estimator/tree/frameworkdev.
- Beyond individualized recourse: Interpretable and interactive summaries of actionable recourses. Advances in Neural Information Processing Systems, 33:12187--12198.
- Interpretable machine learning: Fundamental principles and 10 grand challenges. Statistics Surveys, 16:1--85.
- Counterfactual explanations of machine learning predictions: opportunities and challenges for AI safety. In SafeAI @ AAAI.
- A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access, 9:11974--12001.
- Counterfactual explanations and algorithmic recourses for machine learning: A review. arXiv preprint arXiv:2010.10596.
- Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law & Technology, 31:841--887.
- Explaining groups of instances counterfactually for xai: A use case, algorithm and user study for group-counterfactuals. arXiv preprint arXiv:2303.09297.
- Uncovering interpretable potential confounders in electronic medical records. Nature Communications, 13(1):1014.
- Interpretable classification models for recidivism prediction. Journal of the Royal Statistical Society: Series A, 180(3):689--722.
- ‘‘Why Should You Trust My Explanation?" Understanding Uncertainty in LIME Explanations. arXiv preprint arXiv:1904.12991.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.