Abstract
One of the challenges of deploying machine learning (ML) systems is fairness. Datasets often include sensitive features, which ML algorithms may unwittingly use to create models that exhibit unfairness. Past work on fairness offers no formal guarantees in their results. This paper proposes to exploit formal reasoning methods to tackle fairness. Starting from an intuitive criterion for fairness of an ML model, the paper formalises it, and shows how fairness can be represented as a decision problem, given some logic representation of an ML model. The same criterion can also be applied to assessing bias in training data. Moreover, we propose a reasonable set of axiomatic properties which no other definition of dataset bias can satisfy. The paper also investigates the relationship between fairness and explainability, and shows that approaches for computing explanations can serve to assess fairness of particular predictions. Finally, the paper proposes SAT-based approaches for learning fair ML models, even when the training data exhibits bias, and reports experimental trials.
This work was partially funded by ANITI, funded by the French program “Investing for the Future – PIA3” under Grant agreement n\(^{o}\) ANR-19-PI3A-0004.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Real-value features can be discretized. Moreover, to focus on binary features, the fairly standard one-hot-encoding [58] is assumed for handling non-binary categorical features.
- 2.
For a number of reasons, datasets can contain such protected features, but their removal may be undesirable, for example, because this may induce inconsistencies in datasets.
- 3.
It should be noted that, in ML settings, logic-based models that are not 100% accurate are expected to be less sensitive to overfitting. Thus, the fact that some accuracy is lost is not necessarily a drawback [8].
References
Adebayo, J.A.: FairML: ToolBox for diagnosing bias in predictive modeling. Master’s thesis, Massachusetts Institute of Technology (2016)
Adebayo, J.A.: FairML: auditing black-box predictive models (2017)
Aïvodji, U., Arai, H., Fortineau, O., Gambs, S., Hara, S., Tapp, A.: Fairwashing: the risk of rationalization. In: ICML, pp. 161–170 (2019)
Aïvodji, U., Ferry, J., Gambs, S., Huguet, M., Siala, M.: Learning fair rule lists. CoRR abs/1909.03977 (2019). http://arxiv.org/abs/1909.03977
Angelino, E., Larus-Stone, N., Alabi, D., Seltzer, M., Rudin, C.: Learning certifiably optimal rule lists for categorical data. J. Mach. Learn. Res. 18, 234:1–234:78 (2017)
Angwin, J., Larson, J., Mattu, S., Kirchner, L.: Machine bias. propublica.org, May 2016. http://tiny.cc/a3b3iz
Berk, R., Heidari, H., Jabbari, S., Kearns, M., Roth, A.: Fairness in criminal justice risk assessments: the state of the art. Sociol. Methods Res. (2017). https://doi.org/10.1177/0049124118782533
Berkman, N.C., Sandholm, T.W.: What should be minimized in a decision tree: a re-examination. Department of Computer Science (1995)
Bessiere, C., Hebrard, E., O’Sullivan, B.: Minimising decision tree size as combinatorial optimisation. In: Gent, I.P. (ed.) CP 2009. LNCS, vol. 5732, pp. 173–187. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04244-7_16
Biere, A., Heule, M., van Maaren, H., Walsh, T. (eds.): Handbook of Satisfiability, Frontiers in Artificial Intelligence and Applications, vol. 185. IOS Press (2009)
Bird, S., Hutchinson, B., Kenthapadi, K., Kiciman, E., Mitchell, M.: Fairness-aware machine learning: practical challenges and lessons learned. In: KDD, pp. 3205–3206 (2019)
Cardelli, L., Kwiatkowska, M., Laurenti, L., Paoletti, N., Patane, A., Wicker, M.: Statistical guarantees for the robustness of Bayesian neural networks. In: Kraus, S. (ed.) Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, 10–16 August 2019, pp. 5693–5700. ijcai.org (2019). https://doi.org/10.24963/ijcai.2019/789
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: KDD, pp. 785–794 (2016)
Chouldechova, A.: Fair prediction with disparate impact: a study of bias in recidivism prediction instruments. Big Data 5(2), 153–163 (2017)
Chouldechova, A., Roth, A.: A snapshot of the frontiers of fairness in machine learning. Commun. ACM 63(5), 82–89 (2020)
Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., Huq, A.: Algorithmic decision making and the cost of fairness. In: KDD 2017, pp. 797–806 (2017)
Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 3rd edn. MIT Press (2009). http://mitpress.mit.edu/books/introduction-algorithms
Demsar, J., et al.: Orange: data mining toolbox in python. J. Mach. Learn. Res. 14(1), 2349–2353 (2013)
Dressel, J., Farid, H.: The accuracy, fairness, and limits of predicting recidivism. Sci. Adv. 4(1), eaao5580 (2018)
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.: Fairness through awareness. In: ITCS, pp. 214–226 (2012)
Eén, N., Sörensson, N.: An extensible SAT-solver. In: Giunchiglia, E., Tacchella, A. (eds.) SAT 2003. LNCS, vol. 2919, pp. 502–518. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24605-3_37
Ehlers, R.: Formal verification of piece-wise linear feed-forward neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 269–286. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68167-2_19
European Union High-Level Expert Group on Artificial Intelligence: Ethics guidelines for trustworthy AI, April 2019. https://ec.europa.eu/digital-single-market/en/news/ethics-guidelines-trustworthy-ai
Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., Venkatasubramanian, S.: Certifying and removing disparate impact. In: KDD, pp. 259–268. ACM (2015)
Friedler, S.A., Scheidegger, C., Venkatasubramanian, S.: On the (im)possibility of fairness. CoRR abs/1609.07236 (2016). http://arxiv.org/abs/1609.07236
Friedler, S.A., Scheidegger, C., Venkatasubramanian, S., Choudhary, S., Hamilton, E.P., Roth, D.: A comparative study of fairness-enhancing interventions in machine learning. In: FAT, pp. 329–338 (2019)
Galhotra, S., Brun, Y., Meliou, A.: Fairness testing: testing software for discrimination. In: FSE, pp. 498–510 (2017)
Garg, S., Perot, V., Limtiaco, N., Taly, A., Chi, E.H., Beutel, A.: Counterfactual fairness in text classification through robustness. In: AIES, pp. 219–226 (2019)
Gario, M., Micheli, A.: PySMT: a solver-agnostic library for fast prototyping of SMT-based algorithms. In: SMT Workshop (2015)
Ghosh, B., Meel, K.S.: IMLI: an incremental framework for MaxSAT-based learning of interpretable classification rules. In: AIES, pp. 203–210 (2019)
Grgic-Hlaca, N., Zafar, M.B., Gummadi, K.P., Weller, A.: The case for process fairness in learning: feature selection for fair decision making. In: NIPS Symposium on Machine Learning and the Law (2016)
Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. Morgan Kaufmann (2012)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 3315–3323 (2016). http://papers.nips.cc/paper/6374-equality-of-opportunity-in-supervised-learning
Holstein, K., Vaughan, J.W., Daumé III, H., Dudík, M., Wallach, H.M.: Improving fairness in machine learning systems: what do industry practitioners need? In: CHI, p. 600 (2019)
Hu, H., Siala, M., Hebrard, E., Huguet, M.J.: Learning optimal decision trees with MaxSAT and its integration in AdaBoost. In: IJCAI, pp. 1170–1176 (2020)
Hu, X., Rudin, C., Seltzer, M.: Optimal sparse decision trees. In: NeurIPS, pp. 7265–7273 (2019)
Huang, X., Kwiatkowska, M., Wang, S., Wu, M.: Safety verification of deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 3–29. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_1
Ignatiev, A., Morgado, A., Marques-Silva, J.: PySAT: a python toolkit for prototyping with SAT oracles. In: Beyersdorff, O., Wintersteiger, C.M. (eds.) SAT 2018. LNCS, vol. 10929, pp. 428–437. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-94144-8_26
Ignatiev, A., Narodytska, N., Marques-Silva, J.: Abduction-based explanations for machine learning models. In: AAAI, pp. 1511–1519 (2019)
Ignatiev, A., Narodytska, N., Marques-Silva, J.: On validating, repairing and refining heuristic ML explanations. CoRR abs/1907.02509 (2019). http://arxiv.org/abs/1907.02509
Ignatiev, A., Pereira, F., Narodytska, N., Marques-Silva, J.: A SAT-based approach to learn explainable decision sets. In: IJCAR, pp. 627–645 (2018)
Kamath, A.P., Karmarkar, N., Ramakrishnan, K.G., Resende, M.G.C.: A continuous approach to inductive inference. Math. Program. 57, 215–238 (1992)
Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 97–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_5
Katz, G., et al.: The marabou framework for verification and analysis of deep neural networks. In: Dillig, I., Tasiran, S. (eds.) CAV 2019. LNCS, vol. 11561, pp. 443–452. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-25540-4_26
Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., Schölkopf, B.: Avoiding discrimination through causal reasoning. In: NeurIPS, pp. 656–666 (2017)
Kleinberg, J.M., Mullainathan, S., Raghavan, M.: Inherent trade-offs in the fair determination of risk scores. In: 8th Innovations in Theoretical Computer Science Conference, ITCS 2017, Berkeley, CA, USA, 9–11 January 2017, pp. 43:1–43:23 (2017)
Kohavi, R.: Scaling up the accuracy of Naive-Bayes classifiers: a decision-tree hybrid. In: KDD, pp. 202–207 (1996)
Kusner, M.J., Loftus, J.R., Russell, C., Silva, R.: Counterfactual fairness. In: NeurIPS, pp. 4066–4076 (2017)
Lakkaraju, H., Bach, S.H., Leskovec, J.: Interpretable decision sets: a joint framework for description and prediction. In: KDD, pp. 1675–1684 (2016)
Leofante, F., Narodytska, N., Pulina, L., Tacchella, A.: Automated verification of neural networks: advances, challenges and perspectives. CoRR abs/1805.09938 (2018). http://arxiv.org/abs/1805.09938
Maliotov, D., Meel, K.S.: MLIC: a MaxSAT-based framework for learning interpretable classification rules. In: Hooker, J. (ed.) CP 2018. LNCS, vol. 11008, pp. 312–327. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-98334-9_21
de Moura, L., Bjørner, N.: Z3: an efficient SMT solver. In: Ramakrishnan, C.R., Rehof, J. (eds.) TACAS 2008. LNCS, vol. 4963, pp. 337–340. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-78800-3_24
Nabi, R., Shpitser, I.: Fair inference on outcomes. In: AAAI, pp. 1931–1940 (2018)
Narayanan, A.: Translation tutorial: 21 fairness definitions and their politics. In: FAT (2018)
Narodytska, N.: Formal analysis of deep binarized neural networks. In: IJCAI, pp. 5692–5696 (2018)
Narodytska, N., Ignatiev, A., Pereira, F., Marques-Silva, J.: Learning optimal decision trees with SAT. In: IJCAI, pp. 1362–1368 (2018)
Narodytska, N., Kasiviswanathan, S.P., Ryzhyk, L., Sagiv, M., Walsh, T.: Verifying properties of binarized deep neural networks. In: AAAI, pp. 6615–6624 (2018)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
du Pin Calmon, F., Wei, D., Vinzamuri, B., Ramamurthy, K.N., Varshney, K.R.: Optimized pre-processing for discrimination prevention. In: NeurIPS, pp. 3992–4001 (2017)
Pulina, L., Tacchella, A.: An abstraction-refinement approach to verification of artificial neural networks. In: Touili, T., Cook, B., Jackson, P. (eds.) CAV 2010. LNCS, vol. 6174, pp. 243–257. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-14295-6_24
Ruan, W., Huang, X., Kwiatkowska, M.: Reachability analysis of deep neural networks with provable guarantees. In: IJCAI, pp. 2651–2659 (2018)
Shih, A., Choi, A., Darwiche, A.: A symbolic approach to explaining Bayesian network classifiers. In: IJCAI, pp. 5103–5111 (2018)
Supreme Court of the United States: Ricci v. DeStefano. U.S. 557, 174 (2009)
Verma, S., Rubin, J.: Fairness definitions explained. In: FairWare@ICSE, pp. 1–7 (2018)
Verwer, S., Zhang, Y.: Learning decision trees with flexible constraints and objectives using integer optimization. In: Salvagnin, D., Lombardi, M. (eds.) CPAIOR 2017. LNCS, vol. 10335, pp. 94–103. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59776-8_8
Verwer, S., Zhang, Y.: Learning optimal classification trees using a binary linear program formulation. In: AAAI, pp. 1625–1632 (2019)
Wu, M., Wicker, M., Ruan, W., Huang, X., Kwiatkowska, M.: A game-based approximate verification of deep neural networks with provable guarantees. Theor. Comput. Sci. 807, 298–329 (2020). https://doi.org/10.1016/j.tcs.2019.05.046
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ignatiev, A., Cooper, M.C., Siala, M., Hebrard, E., Marques-Silva, J. (2020). Towards Formal Fairness in Machine Learning. In: Simonis, H. (eds) Principles and Practice of Constraint Programming. CP 2020. Lecture Notes in Computer Science(), vol 12333. Springer, Cham. https://doi.org/10.1007/978-3-030-58475-7_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-58475-7_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58474-0
Online ISBN: 978-3-030-58475-7
eBook Packages: Computer ScienceComputer Science (R0)