Finding Regions of Counterfactual Explanations via Robust Optimization

References

• Anderson R, Huchette J, Ma W, Tjandraatmadja C, Vielma JP (2020) Strong mixed-integer programming formulations for trained neural networks. Math. Programming 183(1–2):3–39.Crossref, Google Scholar
• Artelt A, Vaquet V, Velioglu R, Hinder F, Brinkrolf J, Schilling M, Hammer B (2021) Evaluating robustness of counterfactual explanations. 2021 IEEE Sympos. Ser. Comput. Intelligence (SSCI) (IEEE, Piscataway, NJ), 01–09.Google Scholar
• Ben-Tal A, El Ghaoui L, Nemirovski A (2009) Robust Optimization (Princeton University Press, Princeton, NJ).Crossref, Google Scholar
• Bertsimas D, Dunning I, Lubin M (2016) Reformulation vs. cutting-planes for robust optimization: A computational study. Comput. Management Sci. 13:195–217.Crossref, Google Scholar
• Bienstock D, Özbay N (2008) Computing robust basestock levels. Discrete Optim. 5(2):389–414.Crossref, Google Scholar
• Black E, Wang Z, Fredrikson M, Datta A (2021) Consistent counterfactuals for deep models. Preprint, submitted October 6, https://arxiv.org/abs/2110.03109.Google Scholar
• Bui N, Nguyen D, Nguyen VA (2022) Counterfactual plans under distributional ambiguity. Preprint, submitted April 10, https://arxiv.org/abs/2201.12487.Google Scholar
• Carrizosa E, Ramírez-Ayerbe J, Morales DR (2021) Generating collective counterfactual explanations in score-based classification via mathematical optimization. Expert Systems Appl. 238(D):121954.Google Scholar
• Cplex II (2009) V12. 1: User’s manual for CPLEX. International Business Machines Corporation 46(53):157. Accessed February 12, 2024, https://public.dhe.ibm.com/software/websphere/ilog/docs/optimization/cplex/ps_usrmancplex.pdf.Google Scholar
• Dandl S, Molnar C, Binder M, Bischl B (2020) Multi-objective counterfactual explanations. Bäck T, Preuss M, Deutz A, Wang H, Doerr C, Emmerich M, Trautmann H, eds. Parallel Problem Solving from Nature—PPSN XVI (Springer International Publishing, Cham, Switzerland), 448–469.Crossref, Google Scholar
• Dominguez-Olmedo R, Karimi AH, Schölkopf B (2022) On the adversarial robustness of causal algorithmic recourse. Chaudhuri K, Jegelka S, Song L, Szepesvari C, Niu G, Sabato S, eds. Proc. 39th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research (PMLR, New York), 5324–5342.Google Scholar
• Dua D, Graff C (2017) UCI machine learning repository. Accessed February 14, 2024, http://archive.ics.uci.edu.Google Scholar
• Dutta S, Long J, Mishra S, Tilli C, Magazzeni D (2022) Robust counterfactual explanations for tree-based ensembles. Chaudhuri K, Jegelka S, Song L, Szepesvari C, Niu G, Sabato S, eds. Proc. 39th Internat. Conf. Machine Learn., vol. 162 (PMLR, New York), 5742–5756.Google Scholar
• Ferrario A, Loi M (2022) The robustness of counterfactual explanations over time. IEEE Access 10:82736–82750.Crossref, Google Scholar
• Fischetti M, Jo J (2018) Deep neural networks and mixed integer linear optimization. Constraints 23(3):296–309.Crossref, Google Scholar
• Forel A, Parmentier A, Vidal T (2022) Robust counterfactual explanations for random forests. Preprint, submitted, May 27, https://arxiv.org/abs/2205.14116.Google Scholar
• Grimstad B, Andersson H (2019) ReLU networks as surrogate models in mixed-integer linear programs. Comput. Chemical Engrg. 131:106580.Crossref, Google Scholar
• Gurobi Optimization LLC (2022) Gurobi optimizer reference manual. Accessed February 14, 2024, https://www.gurobi.com.Google Scholar
• Kanamori K, Takagi T, Kobayashi K, Ike Y, Uemura K, Arimura H (2021) Ordered counterfactual explanation by mixed-integer linear optimization. Proc. Conf. AAAI Artificial Intelligence 35(13):11564–11574.Crossref, Google Scholar
• Karimi AH, Barthe G, Balle B, Valera I (2020) Model-agnostic counterfactual explanations for consequential decisions. Chiappa S, Calandra R, eds. Proc. Twenty Third Internat. Conf. Artificial Intelligence Statist., vol. 108 (PMLR), 895–905.Google Scholar
• Mahajan D, Tan C, Sharma A (2019) Preserving causal constraints in counterfactual explanations for machine learning classifiers. Preprint, submitted December 6, https://arxiv.org/abs/1912.03277.Google Scholar
• Maragno D, Röber TE, Birbil I (2022) Counterfactual explanations using optimization with constraint learning. Preprint December 14, https://arxiv.org/abs/2209.10997.Google Scholar
• Maragno D, Wiberg H, Bertsimas D, Birbil SI, den Hertog D, Fajemisin A (2023) Mixed-integer optimization with constraint learning. Oper. Res., epub ahead of print December 1, https://doi.org/10.1287/opre.2021.0707.Google Scholar
• Mothilal RK, Sharma A, Tan C (2020) Explaining machine learning classifiers through diverse counterfactual explanations. Proc. 2020 Conf. Fairness Accountability Transparency (Association for Computing Machinery, New York), 607–617.Google Scholar
• Mutapcic A, Boyd S (2009) Cutting-set methods for robust convex optimization with pessimizing oracles. Optim. Methods Software 24(3):381–406.Crossref, Google Scholar
• Parmentier A, Vidal T (2021) Optimal counterfactual explanations in tree ensembles. Meila M, Zhang T, eds. Proc. 38th Internat. Conf. Machine Learn., vol. 139 (PMLR, New York), 8422–8431.Google Scholar
• Pawelczyk M, Datta T, van-den Heuvel J, Kasneci G, Lakkaraju H (2022) Probabilistically robust recourse: Navigating the trade-offs between costs and robustness in algorithmic recourse. Preprint, submitted March 13, https://arxiv.org/abs/2203.06768.Google Scholar
• Rawal K, Kamar E, Lakkaraju H (2020) Algorithmic recourse in the wild: Understanding the impact of data and model shifts. Preprint, submitted December 22, https://arxiv.org/abs/2012.11788.Google Scholar
• Russell C (2019) Efficient search for diverse coherent explanations. Proc. Conf. Fairness Accountability Transparency (Association for Computing Machinery, New York), 20–28.Google Scholar
• Slack D, Hilgard A, Lakkaraju H, Singh S (2021) Counterfactual explanations can be manipulated. Ranzato M, Beygelzimer A, Dauphin Y, Liang P, Vaughan JW, eds. Advances in Neural Information Processing Systems, vol. 34 (Curran Associates, Inc., Red Hook, NY), 62–75.Google Scholar
• Upadhyay S, Joshi S, Lakkaraju H (2021) Toward robust and reliable algorithmic recourse. Ranzato M, Beygelzimer A, Dauphin Y, Liang P, Vaughan JW, eds. Advances in Neural Information Processing Systems, vol. 34 (Curran Associates, Inc., Red Hook, NY), 16926–16937.Google Scholar
• Ustun B, Spangher A, Liu Y (2019) Actionable recourse in linear classification. Proc. Conf. Fairness Accountability Transparency (Association for Computing Machinery, New York), 10–19.Google Scholar
• Virgolin M, Fracaros S (2023) On the robustness of sparse counterfactual explanations to adverse perturbations. Artificial Intelligence 316:103840.Crossref, Google Scholar
• Wachter S, Mittelstadt B, Russell C (2018) Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard J. Law Tech. 31(2):841–887.Google Scholar