Skip to main content
Springer Nature Link
Log in

Leveraging Group Contrastive Explanations for Handling Fairness

  • Conference paper
  • First Online:
Explainable Artificial Intelligence (xAI 2023)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1903))

Included in the following conference series:

  • 1129 Accesses

Abstract

With the increasing adoption of Artificial Intelligence (AI) for decision-making processes by companies, developing systems that behave fairly and do not discriminate against specific groups of people becomes crucial. Reaching this objective requires a multidisciplinary approach that includes domain experts, data scientists, philosophers, and legal experts, to ensure complete accountability for algorithmic decisions. In such a context, Explainable AI (XAI) plays a key role in enabling professionals from different backgrounds to comprehend the functioning of automatized decision-making processes and, consequently, being able to identify the presence of fairness issues. This paper presents FairX, an innovative approach that uses Group-Contrastive (G-contrast) explanations to estimate whether different decision criteria apply among distinct population subgroups. FairX provides actionable insights through a comprehensive explanation of the decision-making process, enabling businesses to: detect the presence of direct discrimination on the target variable and choose the most appropriate fairness framework.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Compared to the notation in previous chapters, \(X=(R,Q)\), \(S=A\) and \(Y=Y\). Historical bias is generated using \(l_{hr} = 1.5\). Measurement bias is generated using \(l_{my} = 1.5\). For further detail on the data generation framework, see github.com/rcrupiISP/ISParity and [5].

References

  1. Agarwal, A., Agarwal, H.: A seven-layer model with checklists for standardising fairness assessment throughout the AI lifecycle. AI Ethics 1–16 (2023)

    Google Scholar 

  2. Aghaei, S., Azizi, M.J., Vayanos, P.: Learning optimal and fair decision trees for non-discriminative decision-making. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 1418–1426 (2019)

    Google Scholar 

  3. Alimonda, N., Castelnovo, A., Crupi, R., Mercorio, F., Mezzanzanica, M.: Preserving utility in fair top-k ranking with intersectional bias. In: Boratto, L., Faralli, S., Marras, M., Stilo, G. (eds.) BIAS 2023. CCIS, vol. 1840, pp. 59–73. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-37249-0_5

    Chapter  Google Scholar 

  4. Barocas, S., Hardt, M., Narayanan, A.: Fairness and Machine Learning. fairmlbook.org (2019). http://www.fairmlbook.org

  5. Baumann, J., Castelnovo, A., Crupi, R., Inverardi, N., Regoli, D.: Bias on demand: a modelling framework that generates synthetic data with bias. In: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, pp. 1002–1013 (2023)

    Google Scholar 

  6. Baumann, J., Castelnovo, A., Crupi, R., Inverardi, N., Regoli, D.: An open-source toolkit to generate biased datasets (2023)

    Google Scholar 

  7. Begley, T., Schwedes, T., Frye, C., Feige, I.: Explainability for fair machine learning. arXiv preprint arXiv:2010.07389 (2020)

  8. Binns, R.: On the apparent conflict between individual and group fairness. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 514–524 (2020)

    Google Scholar 

  9. Cambria, E., Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: A survey on XAI and natural language explanations. Inf. Process. Manag. 60(1), 103111 (2023)

    Article  Google Scholar 

  10. Castelnovo, A., Cosentini, A., Malandri, L., Mercorio, F., Mezzanzanica, M.: FFTree: a flexible tree to handle multiple fairness criteria. Inf. Process. Manag. 59(6), 103099 (2022)

    Article  Google Scholar 

  11. Castelnovo, A., et al.: Befair: addressing fairness in the banking sector. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 3652–3661. IEEE (2020)

    Google Scholar 

  12. Castelnovo, A., Crupi, R., Greco, G., Regoli, D., Penco, I.G., Cosentini, A.C.: The zoo of fairness metrics in machine learning (2021)

    Google Scholar 

  13. Castelnovo, A., Crupi, R., Greco, G., Regoli, D., Penco, I.G., Cosentini, A.C.: A clarification of the nuances in the fairness metrics landscape. Sci. Rep. 12(1), 4209 (2022)

    Article  Google Scholar 

  14. Castelnovo, A., Malandri, L., Mercorio, F., Mezzanzanica, M., Cosentini, A.: Towards fairness through time. In: Kamp, M., et al. (eds.) ECML PKDD 2021. CCIS, vol. 1524, pp. 647–663. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-93736-2_46

    Chapter  Google Scholar 

  15. Corbett-Davies, S., Goel, S.: The measure and mismeasure of fairness: a critical review of fair machine learning. arXiv preprint arXiv:1808.00023 (2018)

  16. Crupi, R., Castelnovo, A., Regoli, D., San Miguel Gonzalez, B.: Counterfactual explanations as interventions in latent space. Data Mining Knowl. Discov. 1–37 (2022)

    Google Scholar 

  17. Dieterich, W., Mendoza, C., Brennan, T.: Compas risk scales: demonstrating accuracy equity and predictive parity. Northpointe Inc. (2016)

    Google Scholar 

  18. Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.: Fairness through awareness. In: TCSC, pp. 214–226 (2012)

    Google Scholar 

  19. Flores, A.W., Bechtel, K., Lowenkamp, C.T.: False positives, false negatives, and false analyses: a rejoinder to machine bias: there’s software used across the country to predict future criminals. and it’s biased against blacks. Fed. Probat. 80, 38 (2016)

    Google Scholar 

  20. Franklin, J.S., Bhanot, K., Ghalwash, M., Bennett, K.P., McCusker, J., McGuinness, D.L.: An ontology for fairness metrics. In: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, pp. 265–275 (2022)

    Google Scholar 

  21. Friedler, S.A., Scheidegger, C., Venkatasubramanian, S.: The (im) possibility of fairness: different value systems require different mechanisms for fair decision making. Commun. ACM 64(4), 136–143 (2021)

    Article  Google Scholar 

  22. Grabowicz, P., Perello, N., Mishra, A.: Marrying fairness and explainability in supervised learning. In: 2022 ACM FAccT, pp. 1905–1916 (2022)

    Google Scholar 

  23. Green, T.K.: The future of systemic disparate treatment law. Berkeley J. Emp. Lab. L. 32, 395 (2011)

    Google Scholar 

  24. Hertweck, C., Heitz, C., Loi, M.: On the moral justification of statistical parity. In: Proceedings of the 2021 ACM FAccT, pp. 747–757 (2021)

    Google Scholar 

  25. Hilton, D.J.: Conversational processes and causal explanation. Psychol. Bull. 107(1), 65 (1990)

    Article  Google Scholar 

  26. Hu, L., Immorlica, N., Vaughan, J.W.: The disparate effects of strategic manipulation. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, pp. 259–268 (2019)

    Google Scholar 

  27. Jobin, A., Ienca, M., Vayena, E.: The global landscape of AI ethics guidelines. Nat. Mach. Intell. 1(9), 389–399 (2019)

    Article  Google Scholar 

  28. Lipton, P.: Contrastive explanation. R. Inst. Philos. Suppl. 27, 247–266 (1990)

    Article  Google Scholar 

  29. Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  30. Madaio, M.A., Stark, L., Wortman Vaughan, J., Wallach, H.: Co-designing checklists to understand organizational challenges and opportunities around fairness in AI. In: 2020 CHI Conference on HFCS, pp. 1–14 (2020)

    Google Scholar 

  31. Makhlouf, K., Zhioua, S., Palamidessi, C.: On the applicability of machine learning fairness notions. ACM SIGKDD 23(1), 14–23 (2021)

    Article  Google Scholar 

  32. Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: Convxai: a system for multimodal interaction with any black-box explainer. Cogn. Comput. 15(2), 613–644 (2023)

    Google Scholar 

  33. Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A.: Contrxt: generating contrastive explanations from any text classifier. Inf. Fusion 81, 103–115 (2022)

    Article  Google Scholar 

  34. Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A.: The good, the bad, and the explainer: a tool for contrastive explanations of text classifiers. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23–29 July 2022, pp. 5936–5939. ijcai.org (2022). https://doi.org/10.24963/ijcai.2022/858

  35. Malandri, L., Mercorio, F., Mezzanzanica, M., Seveso, A.: Model-contrastive explanations through symbolic reasoning. Decis. Support Syst. 114040 (2023). https://doi.org/10.1016/j.dss.2023.114040. https://doi.org/www.sciencedirect.com/science/article/pii/S016792362300115X

  36. Manerba, M.M., Guidotti, R.: Fairshades: fairness auditing via explainability in abusive language detection systems. In: 2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI), pp. 34–43. IEEE (2021)

    Google Scholar 

  37. Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. (CSUR) 54(6), 1–35 (2021)

    Article  Google Scholar 

  38. Miller, C.C.: Can an algorithm hire better than a human. The New York Times, vol. 25 (2015)

    Google Scholar 

  39. Miller, C.C.: When algorithms discriminate. The New York Times, vol. 9 (2015)

    Google Scholar 

  40. Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  41. Mukerjee, A., Biswas, R., Deb, K., Mathur, A.P.: Multi-objective evolutionary algorithms for the risk-return trade-off in bank loan management. Int. Trans. Oper. Res. 9(5), 583–597 (2002)

    Article  MATH  Google Scholar 

  42. Ribeiro, M.T., Wu, T., Guestrin, C., Singh, S.: Beyond accuracy: behavioral testing of NLP models with checklist. arXiv preprint arXiv:2005.04118 (2020)

  43. Ruf, B., Detyniecki, M.: Towards the right kind of fairness in AI. arXiv preprint arXiv:2102.08453 (2021)

  44. Ryan, M., Stahl, B.C.: Artificial intelligence ethics guidelines for developers and users: clarifying their content and normative implications. J. Inf. Commun. Ethics Soc. 19(1), 61–86 (2020)

    Article  Google Scholar 

  45. Saxena, N.A.: Perceptions of fairness. In: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pp. 537–538 (2019)

    Google Scholar 

  46. Shin, D., Park, Y.J.: Role of fairness, accountability, and transparency in algorithmic affordance. Comput. Hum. Behav. 98, 277–284 (2019)

    Article  Google Scholar 

  47. Speicher, T., et al.: A unified approach to quantifying algorithmic unfairness: measuring individual & group unfairness via inequality indices. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2239–2248 (2018)

    Google Scholar 

  48. Sweeney, L.: Discrimination in online ad delivery. Commun. ACM 56(5), 44–54 (2013)

    Article  Google Scholar 

  49. Tadmor, C.T., Hong, Y.Y., Chao, M.M., Wiruchnipawan, F., Wang, W.: Multicultural experiences reduce intergroup bias through epistemic unfreezing. J. Pers. Soc. Psychol. 103(5), 750 (2012)

    Google Scholar 

  50. Van Bouwel, J., Weber, E.: Remote causes, bad explanations? J. Theory Soc. Behav. 32(4), 437–449 (2002)

    Article  Google Scholar 

  51. Verma, S., Rubin, J.: Fairness definitions explained. In: 2018 IEEE/ACM International Workshop on Software Fairness (FairWare), pp. 1–7. IEEE (2018)

    Google Scholar 

  52. Wahl, B., Cossy-Gantner, A., Germann, S., Schwalbe, N.R.: Artificial intelligence (AI) and global health: how can AI contribute to health in resource-poor settings? BMJ Glob. Health 3(4), e000798 (2018)

    Article  Google Scholar 

  53. Wang, H.E., et al.: A bias evaluation checklist for predictive models and its pilot application for 30-day hospital readmission models. J. Am. Med. Inform. Assoc. 29(8), 1323–1333 (2022)

    Article  MathSciNet  Google Scholar 

  54. Warner, R., Sloan, R.H.: Making artificial intelligence transparent: fairness and the problem of proxy variables. CJE 40(1), 23–39 (2021)

    Google Scholar 

  55. Willborn, S.L.: The disparate impact model of discrimination: theory and limits. Am. UL Rev. 34, 799 (1984)

    Google Scholar 

  56. Zafar, M.B., Valera, I., Gomez-Rodriguez, M., Gummadi, K.P.: Fairness constraints: a flexible approach for fair classification. J. Mach. Learn. Res. 20(1), 2737–2778 (2019)

    MathSciNet  MATH  Google Scholar 

  57. Zafar, M.B., Valera, I., Rogriguez, M.G., Gummadi, K.P.: Fairness constraints: mechanisms for fair classification. In: Artificial Intelligence and Statistics, pp. 962–970. PMLR (2017)

    Google Scholar 

  58. Zhou, J., Chen, F., Holzinger, A.: Towards explainability for AI fairness. In: Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, K.R., Samek, W. (eds.) xxAI 2020. LNCS, vol. 13200, pp. 375–386. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-04083-2_18

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Data Science and Artificial Intelligence, Intesa Sanpaolo S.p.A., Milan, Italy

    Alessandro Castelnovo & Nicole Inverardi

  2. Department of Informatics, Systems and Communication, University of Milan-Bicocca, Milan, Italy

    Alessandro Castelnovo

  3. Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy

    Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica & Andrea Seveso

  4. CRISP Research Centre crispresearch.eu, University of Milano Bicocca, Milan, Italy

    Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica & Andrea Seveso

Authors
  1. Alessandro Castelnovo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nicole Inverardi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lorenzo Malandri
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fabio Mercorio
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mario Mezzanzanica
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Andrea Seveso
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alessandro Castelnovo .

Editor information

Editors and Affiliations

  1. Technological University Dublin, Dublin, Ireland

    Luca Longo

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Castelnovo, A., Inverardi, N., Malandri, L., Mercorio, F., Mezzanzanica, M., Seveso, A. (2023). Leveraging Group Contrastive Explanations for Handling Fairness. In: Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1903. Springer, Cham. https://doi.org/10.1007/978-3-031-44070-0_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-44070-0_17

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-44069-4

  • Online ISBN: 978-3-031-44070-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics