CARE: coherent actionable recourse based on sound counterfactual explanations
International Journal of Data Science and Analytics - Trang 1-26 - 2022
Tóm tắt
Counterfactual explanation (CE) is a popular post hoc interpretability approach that explains how to obtain an alternative outcome from a machine learning model by specifying minimum changes in the input. In line with this context, when the model’s inputs represent actual individuals, actionable recourse (AR) refers to a personalized CE that prescribes feasible changes according to an individual’s preferences. Hence, the quality of ARs highly depends on the soundness of underlying CEs and the proper incorporation of user preferences. To generate sound CEs, several data-level properties, such as proximity and connectedness, should be taken into account. Meanwhile, personalizing explanations demands fulfilling important user-level requirements, like coherency and actionability. The main obstacles to inclusive consideration of the stated properties are their associated modeling and computational complexity as well as the lack of a systematic approach for making a rigorous trade-off between them based on their importance. This paper introduces CARE, an explanation framework that addresses these challenges by formulating the properties as intuitive and computationally efficient objective functions, organized in a modular hierarchy and optimized using a multi-objective optimization algorithm. The devised modular hierarchy enables the arbitration and aggregation of various properties as well as the generation of CEs and AR by choice. CARE involves individuals through a flexible language for defining preferences, facilitates their choice by recommending multiple ARs, and guides their action steps toward their desired outcome. CARE is a model-agnostic approach for explaining any multi-class classification and regression model in mixed-feature tabular settings. We demonstrate the efficacy of our framework through several validation and benchmark experiments on standard data sets and black box models.
Tài liệu tham khảo
Barrowman, N.: Correlation, causation, and confusion. New Atlantis 43, 23–44 (2014)
Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: Lof: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93–104 (2000)
Callahan, A., Shah, N.H.: Machine learning in healthcare. In: Sheikh, A., Wright, A., Cresswell, K.M., Bates, D.W. (eds.) Key Advances in Clinical Informatics, pp. 279–291. Elsevier, Amsterdam (2017)
Campello, R.J., Moulavi, D., Zimek, A., Sander, J.: Hierarchical density estimates for data clustering, visualization, and outlier detection. ACM Trans. Knowl. Discov. Data (TKDD) 10(1), 1–51 (2015)
Chen, P.Y., Smithson, M., Popovich, P.M.: Correlation: Parametric and Nonparametric Measures (No. 139). SAGE, Thousands Oaks (2002)
Dandl, S., Molnar, C., Binder, M., Bischl, B.: Multi-objective counterfactual explanations. In: International Conference on Parallel Problem Solving from Nature, pp. 448–469. Springer, Berlin (2020)
Deb, K., Jain, H.: An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints. IEEE Trans. Evol. Comput. 18(4), 577–601 (2013)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Dogan, Ü., Glasmachers, T., Igel, C.: A unified view on multi-class support vector classification. J. Mach. Learn. Res. 17(45), 1–32 (2016)
Downs, M., Chu, J.L., Yacoby, Y., Doshi-Velez, F., Pan, W.: Cruds: counterfactual recourse using disentangled subspaces. In: ICML Workshop on Human Interpretability in Machine Learning (2020)
Dua, D., Graff, C.: UCI machine learning repository. University of California, Irvine, School of Information and Computer Sciences (2017). http://archive.ics.uci.edu/ml
Ester, M., Kriegel, H.P., Sander, J., Xu, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, pp. 226–231. AAAI Press (1996)
FICO-Community: HELOC Data Set (2018). https://community.fico.com/s/explainable-machine-learning-challenge
Gower, J.C.: A general coefficient of similarity and some of its properties. Biometrics 27, 857–871 (1971)
Atamtürk, A., Savelsbergh, M.W.: Integer-programming software systems. Ann. Oper. Res. 140(1), 67–124 (2005)
Joshi, S., Koyejo, O., Vijitbenjaronk, W., Kim, B., Ghosh, J.: Towards realistic individual recourse and actionable explanations in black-box decision making systems. arXiv preprint arXiv:1907.09615 (2019)
Kanamori, K., Takagi, T., Kobayashi, K., Arimura, H.: Dace: distribution-aware counterfactual explanation by mixed-integer linear optimization. In: Bessiere, C (Ed) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20. International Joint Conferences on Artificial Intelligence Organization, pp. 2855–2862 (2020)
Karimi, A.H., Barthe, G., Balle, B., Valera, I.: Model-agnostic counterfactual explanations for consequential decisions. In: International Conference on Artificial Intelligence and Statistics, pp. 895–905. PMLR (2020)
Karimi, A.H., Barthe, G., Schölkopf, B., Valera, I.: A survey of algorithmic recourse: contrastive explanations and consequential recommendations. ACM Comput. Surv. (2022). https://doi.org/10.1145/3527848
Karimi, A.H., Schölkopf, B., Valera, I.: Algorithmic recourse: from counterfactual explanations to interventions (2020). arXiv preprint arXiv:2002.06278
Kehl, D.L., Kessler, S.A.: Algorithms in the criminal justice system: assessing the use of risk assessments in sentencing. Berkman Klein Center for Internet & Society (2017)
Kulesza, A., Taskar, B., et al.: Determinantal point processes for machine learning. Found. Trends Mach. Learn. 5(2–3), 123–286 (2012)
Laugel, T., Lesot, M.J., Marsala, C., Detyniecki, M.: Issues with post-hoc counterfactual explanations: a discussion (2019). arXiv preprint arXiv:1906.04774
Laugel, T., Lesot, M.J., Marsala, C., Renard, X., Detyniecki, M.: The dangers of post-hoc interpretability: unjustified counterfactual explanations (2019). arXiv preprint arXiv:1907.09294
Le, T., Wang, S., Lee, D.: Grace: Generating concise and informative contrastive sample to explain neural network model’s prediction. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 238–248 (2020)
Loh, W.Y.: Classification and regression trees. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 1(1), 14–23 (2011)
Lucic, A., Oosterhuis, H., Haned, H., de Rijke, M.: Focus: flexible optimizable counterfactual explanations for tree ensembles (2019). arXiv preprint arXiv:1911.12199
Mahajan, D., Tan, C., Sharma, A.: Preserving causal constraints in counterfactual explanations for machine learning classifiers. In: CausalML: Machine Learning and Causal Inference for Improved Decision Making Workshop, NeurIPS 2019, Dec 2019
McDonald, G.C.: Ridge regression. Wiley Interdiscip. Rev. Comput. Stat. 1(1), 93–100 (2009)
Mothilal, R.K., Sharma, A., Tan, C.: 2020. Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 607–617 (2020)
Pawelczyk, M., Broelemann, K., Kasneci, G.: Learning model-agnostic counterfactual explanations for tabular data. In: Proceedings of The Web Conference, pp. 3126–3132 (2020)
Poyiadzi, R., Sokol, K., Santos-Rodriguez, R., De Bie, T., Flach, P.: Face: feasible and actionable counterfactual explanations. In: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pp. 344–350 (2020)
ProPublica: Compas data set (2017)
Rasouli, P., Yu, I.C.: Explan: explaining black-box classifiers using adaptive neighborhood generation. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1–9. IEEE (2020)
Ribeiro, M.T., Singh, S., Guestrin, C.: “ why should i trust you?” explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Ruder, S.: An overview of gradient descent optimization algorithms (2016). arXiv preprint arXiv:1609.04747
Sharma, S., Henderson, J., Ghosh, J.: Certifai: a common framework to provide explanations and analyse the fairness and robustness of black-box models. In: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, AIES’20, New York, pp. 166–172. Association for Computing Machinery (2020)
Siddiqi, N.: Credit risk scorecards: developing and implementing intelligent credit scoring, vol. 3. Wiley, Hoboken (2012)
StatLib-Repository: California housing data set (1997)
Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least angle regression. Ann. Stat. 32(2), 407–499 (2004)
Ustun, B., Spangher, A., Liu, Y.: Actionable recourse in linear classification. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, pp. 10–19 (2019)
Van Looveren, A., Klaise, J.: Interpretable counterfactual explanations guided by prototypes. In: Machine Learning and Knowledge Discovery in Databases. Research Track, pp. 650–665. Springer: Cham (2021)
Verma, S., Dickerson, J., Hines, K.: Counterfactual explanations for machine learning: a review (2020). arXiv preprint arXiv:2010.10596
Verma, S., Hines, K., Dickerson, J.P.: Amortized generation of sequential counterfactual explanations for black-box models (2021). arXiv preprint arXiv:2106.03962
Wachter, S., Mittelstadt, B., Russell, C.: Counterfactual explanations without opening the black box: automated decisions and the GDPR. Harv. J. Law Technol. 31, 841 (2017)