Skip to main content
SpringerLink
Log in

Fair Machine Learning Through the Lens of Causality

  • Chapter
  • First Online:
Machine Learning for Causal Inference

  • 713 Accesses

Abstract

In this chapter, we present a causality-based framework for fairness-aware machine learning. Leveraging the Structural Causal Models (SCMs) (Pearl (2009) Causality. Cambridge University Press), this framework defines fairness in the categories of direct/indirect discrimination, system/group/individual-level discrimination, and their derivatives, e.g., indirect individual-level discrimination. The framework can unify various causal fairness notions by specifying the causal path sets and observational conditions. Within this causality-based framework, we present three existing causality-based fairness notions, Path-specific Fairness (Zhang et al (2017) A causal framework for discovering and removing direct and indirect discrimination. In: Proceedings of AAAI’17. AAAI Press, pp 3929–3935), Counterfactual Fairness (Wu et al (2019) Counterfactual fairness: unidentification, bound and algorithm. In: Kraus S (ed) Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, 10–16 Aug 2019, pp 1438–1444. https://doi.org/10.24963/ijcai.2019/199), and Path-specific Counterfactual (PC) Fairness (Wu et al (2019) PC-fairness: a unified framework for measuring causality-based fairness. In: Wallach HM et al (eds) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, 8–14 Dec 2019, pp 3399–3409. http://papers.nips.cc/paper/8601-pc-fairness-a-unified-framework-for-measuring-causality-based-fairness). We discuss their definitions, quantification, and integration with machine learning workflows. Then, we present a literature review of related works of fairness modeling from the causality perspective. In the end, we conclude this chapter with a discussion of potential research challenges and future directions in this field, including relaxing the causal assumptions, dealing with causal fairness in sequential settings, and achieving causal fairness in networked data. We expect the chapter to summarize the latest progress in causal fairness and advance the understanding of causality and fairness from modeling, quantification, identification, and machine learning integration.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. P. Adler et al., Auditing black-box models for indirect influence, in 2016 IEEE 16th International Conference on Data Mining (ICDM) (IEEE, 2016), pp. 1–10

    Google Scholar 

  2. C. Agarwal, H. Lakkaraju, M. Zitnik, Towards a unified framework for fair and stable graph representation learning, in Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI 2021, Virtual Event, 27–30 July 2021, ed. by C.P. de Campos, M.H. Maathuis, E. Quaeghebeur. Proceedings of Machine Learning Research, vol. 161 (AUAI Press, 2021), pp. 2114–2124. https://proceedings.mlr.press/v161/agarwal21b.html

  3. C. Avin, I. Shpitser, J. Pearl, Identifiability of path-specific effects, in IJCAI’05 (2005), pp. 357–363

    Google Scholar 

  4. P. Awasthi, M. Kleindessner, J. Morgenstern, Equalized odds postprocessing under imperfect group information, in The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26–28 Aug 2020, Online [Palermo, Sicily], ed. by S. Chiappa, R. Calandra. Proceedings of Machine Learning Research, vol. 108 (PMLR, 2020), pp. 1770–1780. http://proceedings.mlr.press/v108/awasthi20a.html

  5. A. Balke, J. Pearl, Counterfactual probabilities: computational methods, bounds and applications, in UAI’94: Proceedings of the Tenth Annual Conference on Uncertainty in Artificial Intelligence, Seattle, Washington, 29–31 July 1994, pp. 46–54

    Google Scholar 

  6. S. Barocas, M. Hardt, NIPS 2017 Tutorial on Fairness in Machine Learning, 2017. https://mrtz.org/nips17/

  7. A.J. Bose, W.L. Hamilton, Compositional fairness constraints for graph embeddings, in Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, 9–15 June 2019, ed. by K. Chaudhuri, R. Salakhutdinov. Proceedings of Machine Learning Research, vol. 97 (PMLR, 2019), pp. 715–724. http://proceedings.mlr.press/v97/bose19a.html

  8. A. Bower et al., Fair pipelines, in CoRR abs/1707.00391 (2017). arXiv: 1707.00391. http://arxiv.org/abs/1707.00391

  9. M. Buyl, T. De Bie, DeBayes: a Bayesian method for debiasing network embeddings, in Proceedings of the 37th International Conference on Machine Learning, ICML 2020, Virtual Event, 13–18 July 2020. Proceedings of Machine Learning Research, vol. 119 (PMLR, 2020), pp. 1220–1229. http://proceedings.mlr.press/v119/buyl20a.html

  10. T. Calders, F. Kamiran, M. Pechenizkiy, Building classifiers with independency constraints, in ICDM Workshops 2009, IEEE International Conference on Data Mining Workshops, Miami, 6 Dec 2009, ed. by Y. Saygin et al. (IEEE Computer Society, 2009), pp. 13–18. https://doi.org/10.1109/ICDMW.2009.83

    Google Scholar 

  11. T. Calders, S. Verwer, Three Naive Bayes approaches for discrimination-free classification. Data Mining Knowl. Dis. 21(2), 277–292 (2010). https://doi.org/10.1007/s10618-010-0190-x

    Article  MathSciNet  Google Scholar 

  12. Y. Chikahara et al., Learning individually fair classifier with path specific causal-effect constraint, in The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, Virtual Event, 13–15 Apr 2021, ed. by A. Banerjee, K. Fukumizu. Proceedings of Machine Learning Research, vol. 130 (PMLR, 2021), pp. 145–153. http://proceedings.mlr.press/v130/chikahara21a.html

  13. Y. Chikahara et al., Making individually fair predictions with causal pathways, in Data Mining and Knowledge Discovery, 9 Nov 2022. ISSN: 1384-5810, 1573-756X. https://doi.org/10.1007/s10618-022-00885-6 (visited on 13 Nov 2022)

  14. S. Corbett-Davies et al., Algorithmic decision making and the cost of fairness, in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, 13–17 Aug 2017 (ACM, 2017), pp. 797–806. https://doi.org/10.1145/3097983.3098095

  15. E. Dai, S. Wang, Say no to the discrimination: learning fair graph neural networks with limited sensitive attribute information, in WSDM’21, The Fourteenth ACM International Conference on Web Search and Data Mining, Virtual Event, Israel, 8–12 Mar 2021, ed. by L. Lewin-Eytan et al. (ACM, 2021), pp. 680–688. https://doi.org/10.1145/3437963.3441752

    Google Scholar 

  16. Y. Dong et al., Fairness in graph mining: a survey, arXiv preprint (2022)

    Google Scholar 

  17. Y. Dong et al., Individual fairness for graph neural networks: a ranking based approach, in KDD’21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, Singapore, 14–18 Aug 2021, ed. by F. Zhu, B.C. Ooi, C. Miao (ACM, 2021), pp. 300–310. https://doi.org/10.1145/3447548.3467266

  18. C. Dwork, C. Ilvento, Fairness under composition, in 10th Innovations in Theoretical Computer Science Conference, ITCS 2019, San Diego, 10–12 Jan 2019, ed. by A. Blum. LIPIcs. Schloss Dagstuhl – Leibniz-Zentrum für Informatik, vol. 124, 2019, pp. 33:1–33:20. https://doi.org/10.4230/LIPIcs.ITCS.2019.33. arXiv: 1806.06122

  19. C. Dwork, C. Ilvento, M. Jagadeesan, Individual fairness in pipelines, in 1st Symposium on Foundations of Responsible Computing, FORC 2020, 1–3 June 2020, Harvard University, Cambridge, MA (virtual conference), ed. by A. Roth. LIPIcs. Schloss Dagstuhl – Leibniz-Zentrum für Informatik, vol. 156, 2020, pp. 7:1–7:22. https://doi.org/10.4230/LIPIcs.FORC.2020.7

  20. H. Edwards, A.J. Storkey, Censoring representations with an adversary, in 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2–4 May 2016, Conference Track Proceedings, ed. by Y. Bengio, Y. LeCun (2016). http://arxiv.org/abs/1511.05897

  21. V. Emelianov et al., The price of local fairness in multistage selection, in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, 10–16 Aug 2019, ed. by S. Kraus, 2019, pp. 5836–5842. https://doi.org/10.24963/ijcai.2019/809

  22. G. Farnadi, B. Babaki, M. Gendreau, A unifying framework for fairness-aware influence maximization, in Companion of the 2020 Web Conference 2020, Taipei, 20–24 Apr 2020, ed. by A. El Fallah Seghrouchni et al. (ACM/IW3C2, 2020), pp. 714–722. https://doi.org/10.1145/3366424.3383555

  23. M. Feldman et al., Certifying and removing disparate impact, in Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, 2015), pp. 259–268

    Google Scholar 

  24. J. Fisher et al., Debiasing knowledge graph embeddings, in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, 16–20 Nov 2020, ed. by B. Webber et al. (Association for Computational Linguistics, 2020), pp. 7332–7345. https://doi.org/10.18653/v1/2020.emnlp-main.595

    Google Scholar 

  25. S. Garg et al., Counterfactual fairness in text classification through robustness, in Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, AIES 2019, Honolulu, 27–28 Jan 2019, ed. by V. Conitzer, G.K. Hadfield, S. Vallor (ACM, 2019), pp. 219–226. https://doi.org/10.1145/3306618.3317950

  26. S. Gupta, A. Dukkipati, Protecting Individual Interests Across Clusters: Spectral Clustering with Guarantees, 8 May 2021. arXiv: 2105.03714 [cs, stat]. http://arxiv.org/abs/2105.03714 (visited on 01 July 2022)

  27. S. Hajian, J. Domingo-Ferrer, A methodology for direct and indirect discrimination prevention in data mining. IEEE Trans. Knowl. Data Eng. 25(7), 1445–1459 (2013). ISSN: 1041-4347. https://doi.org/10.1109/TKDE.2012.72. http://ieeexplore.ieee.org/document/6175897/

  28. M. Hardt, E. Price, N. Srebro et al., Equality of opportunity in supervised learning, in Advances in Neural Information Processing Systems, 2016, pp. 3315–3323

    Google Scholar 

  29. L. Hu, Y. Chen, A short-term intervention for long-term fairness in the labor market, in Proceedings of the 2018 World Wide Web Conference, 2018, pp. 1389–1398

    Google Scholar 

  30. Y. Hu, L. Zhang, Achieving long-term fairness in sequential decision making (2022), arXiv preprint arXiv:2204.01819

    Google Scholar 

  31. W. Huang, Y. Wu, X. Wu, Multi-cause discrimination analysis using potential outcomes, in Social, Cultural, and Behavioral Modeling, 13rd International Conference, SBP-BRiMS 2020, Washington, DC, 18–21 Oct 2020, Proceedings (Springer, 2020)

    Google Scholar 

  32. W. Huang et al., Fairness through equality of effort, in Companion Proceedings of the Web Conference 2020, 2020, pp. 743–751

    Google Scholar 

  33. F. Kamiran, T. Calders, Classifying without discriminating, in 2009 2nd International Conference on Computer, Control and Communication (IEEE, 2009), pp. 1–6. ISBN: 978-1-4244-3313-1. https://doi.org/10.1109/IC4.2009.4909197. http://ieeexplore.ieee.org/document/4909197/ (visited on 04 Mar 2015)

  34. F. Kamiran, T. Calders, Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1–33 (2012)

    Article  Google Scholar 

  35. F. Kamiran, T. Calders, M. Pechenizkiy, Discrimination aware decision tree learning, in ICDM 2010, the 10th IEEE International Conference on Data Mining, Sydney, 14–17 Dec 2010, ed. by G.I. Webb et al. (IEEE Computer Society, 2010), pp. 869–874. https://doi.org/10.1109/ICDM.2010.50

    Google Scholar 

  36. F. Kamiran, T. Calders, M. Pechenizkiy, Discrimination aware decision tree learning, in 2010 IEEE 10th International Conference on Data Mining (ICDM) (IEEE, 2010), pp. 869–874

    Google Scholar 

  37. F. Kamiran, A. Karim, X. Zhang, Decision theory for discrimination-aware classification, in Proceedings of the 12nd IEEE International Conference on Data Mining (ICDM 2012) (IEEE, 2012), pp. 924–929. ISBN: 978-0-7695-4905-7. https://doi.org/10.1109/ICDM.2012.45

  38. T. Kamishima, S. Akaho, J. Sakuma, Fairness-aware learning through regularization approach, in 2011 IEEE 11th International Conference on Data Mining Workshops (ICDMW), Vancouver, 11 Dec 2011, ed. by M. Spiliopoulou et al. (IEEE Computer Society, 2011), pp. 643–650. https://doi.org/10.1109/ICDMW.2011.83

    Google Scholar 

  39. T. Kamishima et al., Fairness-aware classifier with prejudice remover regularizer, in Machine Learning and Knowledge Discovery in Databases – European Conference, ECML PKDD 2012, Bristol, 24–28 Sep 2012. Proceedings, Part II, ed. by P.A. Flach, T. De Bie, N. Cristianini. Lecture Notes in Computer Science, vol. 7524 (Springer, 2012), pp. 35–50. https://doi.org/10.1007/978-3-642-33486-3_3

  40. J. Kang et al., InFoRM: individual fairness on graph mining, in KDD’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, 23–27 Aug 2020, ed. by R. Gupta et al. (ACM, 2020), pp. 379–389. https://doi.org/10.1145/3394486.3403080

    Google Scholar 

  41. S. Kannan, A. Roth, J. Ziani, Downstream effects of affirmative action, in Proceedings of the Conference on Fairness, Accountability, and Transparency, 2019, pp. 240–248

    Google Scholar 

  42. A. Khademi et al., Fairness in algorithmic decision making: an excursion through the lens of causality, in The World Wide Web Conference, WWW 2019, San Francisco, 13–17 May 2019, ed. by L. Liu et al. (ACM, 2019), pp. 2907–2914. https://doi.org/10.1145/3308558.3313559

    Google Scholar 

  43. N. Kilbertus et al., Avoiding discrimination through causal reasoning, in Advances in Neural Information Processing Systems (2017), pp. 656–666

    Google Scholar 

  44. N. Kilbertus et al., The sensitivity of counterfactual fairness to unmeasured confounding, in Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI 2019, Tel Aviv, 22–25 July 2019, ed. by A. Globerson, R. Silva (AUAI Press, 2019), p. 213. http://auai.org/uai2019/proceedings/papers/213.pdf

  45. H. Kim et al., Counterfactual fairness with disentangled causal effect variational autoencoder, in Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, the Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2–9 Feb 2021 (AAAI Press, 2021), pp. 8128–8136. https://ojs.aaai.org/index.php/AAAI/article/view/16990

  46. D. Koller, N. Friedman, Probabilistic Graphical Models: Principles and Techniques (The MIT Press, Cambridge, MA, 2009). ISBN: 0-262-01319-3. https://books.google.com/books?id=7dzpHCHzNQ4C&pgis=1

  47. E. Krasanakis, S. Papadopoulos, I. Kompatsiaris, Applying fairness constraints on graph node ranks under personalization bias, in Complex Networks & Their Applications IX – Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2020, Madrid, 1–3 Dec 2020, ed. by R.M. Benito et al. Studies in Computational Intelligence, vol. 944 (Springer, 2020), pp. 610–622. https://doi.org/10.1007/978-3-030-65351-4_49

  48. M.J. Kusner et al., Counterfactual fairness, in Advances in Neural Information Processing Systems (2017), pp. 4066–4076

    Google Scholar 

  49. M.J. Kusner et al., Making decisions that reduce discriminatory impacts, in Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, 9–15 June 2019, ed. by K. Chaudhuri, R. Salakhutdinov. Proceedings of Machine Learning Research, vol. 97 (PMLR, 2019), pp. 3591–3600. http://proceedings.mlr.press/v97/kusner19a.html

  50. C. Laclau et al., All of the fairness for edge prediction with optimal transport, in The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, Virtual Event, 13–15 Apr 2021, ed. by A. Banerjee, K. Fukumizu. Proceedings of Machine Learning Research, vol. 130 (PMLR, 2021), pp. 1774–1782. http://proceedings.mlr.press/v130/laclau21a.html

  51. J. Li et al., Discrimination detection by causal effect estimation, in 2017 IEEE International Conference on Big Data, BigData 2017, Boston, 11–14 Dec 2017, ed. by J.-Y. Nie et al. (IEEE Computer Society, 2017), pp. 1087–1094. https://doi.org/10.1109/BigData.2017.8258033

    Google Scholar 

  52. Y. Li et al., Towards personalized fairness based on causal notion, in SIGIR’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, 11–15 July 2021, ed. by F. Diaz et al. (ACM, 2021), pp. 1054–1063. https://doi.org/10.1145/3404835.3462966

    Google Scholar 

  53. M. Lichman, UCI Machine Learning Repository, 2013. http://archive.ics.uci.edu/ml

  54. L. Liu et al., Delayed impact of fair machine learning, in International Conference on Machine Learning (2018), pp. 3156–3164

    Google Scholar 

  55. L.T. Liu et al., The disparate equilibria of algorithmic decision making when individuals invest rationally, in Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (2020), pp. 381–391

    Google Scholar 

  56. C. Louizos et al., Causal effect inference with deep latent-variable models, in Advances in Neural Information Processing Systems (2017), pp. 6446–6456

    Google Scholar 

  57. B.T. Luong, S. Ruggieri, F. Turini, K-NN as an implementation of situation testing for discrimination discovery and prevention, in Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – KDD’11 (ACM Press, New York, 2011), p. 502. ISBN: 978-1-4503-0813-7. https://doi.org/10.1145/2020408.2020488

    Book  Google Scholar 

  58. J. Ma et al., Learning fair node representations with graph counterfactual fairness, in WSDM’22: The Fifteenth ACM International Conference on Web Search and Data Mining, Virtual Event/Tempe, 21–25 Feb 2022, ed. by K. Selcuk Candan et al. (ACM, 2022), pp. 695–703. https://doi.org/10.1145/3488560.3498391

    Google Scholar 

  59. D. Madras et al., Learning adversarially fair and transferable representations, in Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, 10–15 July 2018, ed. by J.G. Dy, A. Krause. Proceedings of Machine Learning Research, vol. 80 (PMLR, 2018), pp. 3381–3390. http://proceedings.mlr.press/v80/madras18a.html

  60. N. Mehrabi et al., A survey on bias and fairness in machine learning. ACM Comput. Surv. 54(6), 115:1–115:35 (2021). https://doi.org/10.1145/3457607

  61. H. Mouzannar, M.I. Ohannessian, N. Srebro, From fair decision making to social equality, in Proceedings of the Conference on Fairness, Accountability, and Transparency (2019), pp. 359–368

    Google Scholar 

  62. R. Nabi, I. Shpitser, Fair inference on outcomes, in Proceedings of AAAI’18, vol. 2018 (2018)

    Google Scholar 

  63. H. Ogura, A. Takeda, Convex fairness constrained model using causal effect estimators, in Companion of the 2020 Web Conference 2020, Taipei, 20–24 Apr 2020, ed. by A. El Fallah Seghrouchni et al. (ACM/IW3C2, 2020), pp. 723–732. https://doi.org/10.1145/3366424.3383556

  64. J. Palowitch, B. Perozzi, Debiasing graph representations via metadata-orthogonal training, in IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2020, The Hague, 7–10 Dec 2020, ed. by M. Atzmüller, M. Coscia, R. Missaoui (IEEE, 2020), pp. 435–442. https://doi.org/10.1109/ASONAM49781.2020.9381348

  65. J. Pearl, Causality, 2nd ed. (Cambridge: Cambridge University Press, 2009)

    Book  MATH  Google Scholar 

  66. D. Pedreshi, S. Ruggieri, F. Turini, Discrimination-aware data mining, in Proceeding of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – KDD 08, New York (ACM Press, New York, 2008), p. 560. ISBN: 978-1-60558-193-4. https://doi.org/10.1145/1401890.1401959

    Book  Google Scholar 

  67. B. Qureshi et al., Causal discrimination discovery through propensity score analysis, CoRRabs/1608.03735 (2016). http://arxiv.org/abs/1608.03735

  68. T.A. Rahman et al., Fairwalk: towards fair graph embedding, in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, 10–16 Aug 2019, ed. by S. Kraus (2019), pp. 3289–3295. https://doi.org/10.24963/ijcai.2019/456

  69. A. Rahmattalabi et al., Exploring algorithmic fairness in robust graph covering problems, in Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, 8–14 Dec 2019, ed. by H.M. Wallach et al. (2019), pp. 15750–15761. http://papers.nips.cc/paper/9707-exploring-algorithmic-fairness-in-robust-graph-covering-problems

  70. A. Romei, S. Ruggieri, A multidisciplinary survey on discrimination analysis. Knowl. Eng. Rev. 29(05), 582–638 (2014). ISSN: 0269-8889. https://doi.org/10.1017/S0269888913000039 (Visited on 04 Mar 2015)

  71. D.B. Rubin, Causal inference using potential outcomes: design, modeling, decisions. J. Am. Stat. Assoc. 100(469), 322–331 (2005)

    Article  MathSciNet  MATH  Google Scholar 

  72. C. Russell et al., When worlds collide: integrating different counterfactual assumptions in fairness, in Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, 4–9 Dec 2017, pp. 6414–6423

    Google Scholar 

  73. P. Sanchez-Martin, M. Rateike, I. Valera, VACA: design of variational graph autoencoders for interventional and counterfactual queries (2021), arXiv preprint arXiv:2110.14690

    Google Scholar 

  74. P. Sattigeri et al., Fairness GAN: generating datasets with fairness properties using a generative adversarial network. IBM J. Res. Dev. 63, 3:1–3:9 (2019). https://doi.org/10.1147/JRD.2019.2945519

  75. R. Scheines et al., The TETRAD project: constraint based aids to causal model specification. Multivar. Behav. Res. 33(1), 65–117 (1998). ISSN: 0027-3171. https://doi.org/10.1207/s15327906mbr3301textunderscore3 (Visited on 26 Oct 2018)

  76. I. Shpitser, Counterfactual graphical models for longitudinal mediation analysis with unobserved confounding. Cogn. Sci. 37(6), 1011–1035 (2013). https://doi.org/10.1111/cogs.12058

    Article  Google Scholar 

  77. I. Shpitser, J. Pearl, Complete identification methods for the causal hierarchy. J. Mach. Learn. Res. 9, 1941–1979 (2008)

    MathSciNet  MATH  Google Scholar 

  78. I. Shpitser, J. Pearl, What counterfactuals can be tested, in UAI 2007, Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence, Vancouver, 19–22 July 2007, pp. 352–359

    Google Scholar 

  79. I. Shpitser et al., Introduction to nested Markov models. Behaviormetrika 41(1), 3–39 (2014)

    Article  MathSciNet  Google Scholar 

  80. P. Spirtes et al., Causation, Prediction, and Search (MIT Press, Cambridge, MA, 2000)

    MATH  Google Scholar 

  81. X. Tang et al., Investigating and mitigating degree-related biases in graph convoltuional networks, in CIKM’20: The 29th ACM International Conference on Information and Knowledge Management, Virtual Event, 19–23 Oct 2020, ed. by M. d’Aquin et al. (ACM, 2020), pp. 1435–1444. https://doi.org/10.1145/3340531.3411872

    Google Scholar 

  82. J. Tian, J. Pearl, A general identification condition for causal effects, in AAAI/IAAI (2002), pp. 567–573

    Google Scholar 

  83. J. Tian, J. Pearl, Probabilities of causation: bounds and identification. Ann. Math. Artif. Intell. 28(1–4), 287–313 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  84. S. Tsioutsiouliklis et al., Fairness-aware PageRank, in WWW’21: The Web Conference 2021, Virtual Event/Ljubljana, 19–23 Apr 2021, ed. by J. Leskovec et al. (ACM/IW3C2, 2021), pp. 3815–3826. https://doi.org/10.1145/3442381.3450065

  85. R. Tu et al., How do fair decisions fare in long-term qualification? in Thirty-Fourth Conference on Neural Information Processing Systems (2020)

    Google Scholar 

  86. J. Vig et al., Investigating gender bias in language models using causal mediation analysis, in Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6–12 Dec 2020, Virtual, ed. by H. Larochelle et al. (2020). https://proceedings.neurips.cc/paper/2020/hash/92650b2e92217715fe312e6fa7b90d82-Abstract.html

  87. Y. Wu, X. Wu, Using loglinear model for discrimination discovery and prevention, in 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA) (IEEE, 2016), pp. 110–119

    Google Scholar 

  88. Y. Wu, L. Zhang, X. Wu, Counterfactual fairness: unidentification, bound and algorithm, in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, 10–16 Aug 2019, ed. by S. Kraus, 2019, pp. 1438–1444. https://doi.org/10.24963/ijcai.2019/199

  89. Y. Wu, L. Zhang, X. Wu, Counterfactual fairness: unidentification, bound and algorithm, in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI (2019), pp. 10–16

    Google Scholar 

  90. Y. Wu, L. Zhang, X. Wu, On convexity and bounds of fairness-aware classification, in The World Wide Web Conference (ACM, 2019), pp. 3356–3362

    Google Scholar 

  91. Y. Wu, L. Zhang, X. Wu, On discrimination discovery and removal in ranked data using causal graph, in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018, London, 19–23 Aug 2018, ed. by Y. Guo, F. Farooq (ACM, 2018), pp. 2536–2544. https://doi.org/10.1145/3219819.3220087

  92. Y. Wu et al., PC-fairness: a unified framework for measuring causality-based fairness, in Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, 8–14 Dec 2019, ed. by H.M. Wallach et al. (2019), pp. 3399–3409. http://papers.nips.cc/paper/8601-pc-fairness-a-unified-framework-for-measuring-causality-based-fairness

  93. Q. Xie et al., Controllable invariance through adversarial feature learning, in Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, 4–9 Dec 2017, ed. by I. Guyon et al. (2017), pp. 585–596. http://papers.nips.cc/paper/6661-controllable-invariance-through-adversarial-feature-learning

  94. D. Xu et al., Achieving causal fairness through generative adversarial networks, in Proceedings of the 28th International Joint Conference on Artificial Intelligence (AAAI Press, 2019), pp. 1452–1458

    Google Scholar 

  95. D. Xu et al., Fairgan: fairness-aware generative adversarial networks, in 2018 IEEE International Conference on Big Data (Big Data) (IEEE, 2018), pp. 570–575

    Google Scholar 

  96. D. Xu et al., FairGAN\({ }^{+}\): achieving fair data generation and classification through generative adversarial nets, in 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, 9–12 Dec 2019 (IEEE, 2019), pp. 1401–1406. https://doi.org/10.1109/BigData47090.2019.9006322

  97. Z. Xu et al., Disentangled Representation with Causal Constraints for Counterfactual Fairness (2022). arXiv: 2208.09147 [cs]. http://arxiv.org/abs/2208.09147 (visited on 23 Aug 2022)

  98. Z. Yang, J. Feng, A causal inference method for reducing gender bias in word embedding relations, in The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, the Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, the Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, 7–12 Feb 2020 (AAAI Press, 2020), pp. 9434–9441. https://aaai.org/ojs/index.php/AAAI/article/view/6486

  99. M.B. Zafar et al., Fairness beyond disparate treatment & disparate impact: learning classification without disparate mistreatment, in Proceedings of the 26th International Conference on World Wide Web, WWW, Perth, 3–7 Apr 2017, ed. by R. Barrett et al. (ACM, 2017), pp. 1171–1180. https://doi.org/10.1145/3038912.3052660

    Google Scholar 

  100. M.B. Zafar et al., Fairness constraints: mechanisms for fair classification, in Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017, Fort Lauderdale, 20–22 Apr 2017, ed. by A. Singh, X. (Jerry) Zhu, Proceedings of Machine Learning Research, vol. 54 (PMLR, 2017), pp. 962–970. http://proceedings.mlr.press/v54/zafar17a.html

  101. R.S. Zemel et al., Learning fair representations. ICML 28, 325–333 (2013)

    Google Scholar 

  102. B.H. Zhang, B. Lemoine, M. Mitchell, Mitigating unwanted biases with adversarial learning, in Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, AIES 2018, New Orleans, 02–03 Feb 2018, ed. by J. Furman et al. (ACM, 2018), pp. 335–340. https://doi.org/10.1145/3278721.3278779

    Google Scholar 

  103. J. Zhang, E. Bareinboim, Equality of opportunity in classification: a causal approach, in Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, Montréal, 3–8 Dec 2018, pp. 3675–3685

    Google Scholar 

  104. J. Zhang, E. Bareinboim, Fairness in decision-making–the causal explanation formula, in 32nd AAAI Conference on Artificial Intelligence (2018)

    Google Scholar 

  105. L. Zhang, Q. Pan, X. Wu, Modeling SNP and quantitative trait association from GWAS catalog using CLG Bayesian network, in 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (IEEE, 2017), pp. 266–269

    Google Scholar 

  106. L. Zhang, Y. Wu, X. Wu, A causal framework for discovering and removing direct and indirect discrimination, in Proceedings of AAAI’17 (AAAI Press, 2017), pp. 3929–3935

    Google Scholar 

  107. L. Zhang, Y. Wu, X. Wu, Achieving non-discrimination in data release, in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, 13–17 Aug 2017 (ACM, 2017), pp. 1335–1344. https://doi.org/10.1145/3097983.3098167

  108. L. Zhang, Y. Wu, X. Wu, Causal modeling-based discrimination discovery and removal: criteria, bounds, and algorithms. IEEE Trans. Knowl. Data Eng. 31(11), 2035–2050 (2019). https://doi.org/10.1109/TKDE.2018.2872988

    Article  Google Scholar 

  109. L. Zhang, Y. Wu, X. Wu, Causal modeling-based discrimination discovery and removal: criteria, bounds, and algorithms. IEEE Trans. Knowl. Data Eng. 31(11), (2019)

    Google Scholar 

  110. L. Zhang, Y. Wu, X. Wu, On discrimination discovery using causal networks, in Proceedings of SBP-BRiMS 2016, 2016

    Google Scholar 

  111. L. Zhang, Y. Wu, X. Wu, Situation testing-based discrimination discovery: a causal inference approach, in Proceedings of IJCAI’16 (2016)

    Google Scholar 

  112. L. Zhang, W. Yongkai, W. Xintao, Tutorial: anti-discrimination learning: a causal modeling-based framework, in KDD (2018)

    Google Scholar 

  113. W. Zhang et al., Fairness Amidst Non-IID Graph Data: A Literature Review, 15 Feb 2022. arXiv: 2202.07170. http://arxiv.org/abs/2202.07170 (visited on 20 Feb 2022)

  114. X. Zhang, M. Khaliligarekani, C. Tekin et al., Group retention when using machine learning in sequential decision making: the interplay between user dynamics and fairness, in Advances in Neural Information Processing Systems (2019), pp. 15269–15278

    Google Scholar 

  115. I. Zliobaite, Measuring discrimination in algorithmic decision making. Data Mining Knowl. Dis. 31(4), 1060–1089 (2017). https://doi.org/10.1007/s10618-017-0506-1

    Article  MathSciNet  Google Scholar 

  116. I. Žliobaite, F. Kamiran, T. Calders, Handling conditional discrimination, in 2011 IEEE 11th International Conference On Data Mining (ICDM) (IEEE, 2011), pp. 992–1001

    Google Scholar 

Download references

Acknowledgements

This work was supported in part by NSF 1910284, 1946391, 2142725, and 2147375.

Author information

Authors and Affiliations

  1. Clemson University, Clemson, SC, USA

    Yongkai Wu

  2. University of Arkansas, Fayetteville, AR, USA

    Lu Zhang & Xintao Wu

Authors
  1. Yongkai Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xintao Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yongkai Wu .

Editor information

Editors and Affiliations

  1. University of Virginia, Charlottesville, VA, USA

    Sheng Li

  2. Ant Group, Hangzhou, China

    Zhixuan Chu

Rights and permissions

Reprints and permissions

Copyright information

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

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Wu, Y., Zhang, L., Wu, X. (2023). Fair Machine Learning Through the Lens of Causality. In: Li, S., Chu, Z. (eds) Machine Learning for Causal Inference. Springer, Cham. https://doi.org/10.1007/978-3-031-35051-1_6

Download citation

Publish with us

Policies and ethics

Search

Navigation