Papers
Topics
Authors
Recent
Search
2000 character limit reached

fairret: a Framework for Differentiable Fairness Regularization Terms

Published 26 Oct 2023 in cs.LG | (2310.17256v2)

Abstract: Current fairness toolkits in machine learning only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines. We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular, flexible objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. One-Network Adversarial Fairness. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01):2412–2420, July 2019. ISSN 2374-3468. doi: 10.1609/aaai.v33i01.33012412.
  2. A Reductions Approach to Fair Classification. In Proceedings of the 35th International Conference on Machine Learning, pp.  60–69. PMLR, July 2018.
  3. A rewriting system for convex optimization problems. Journal of Control and Decision, 5(1):42–60, 2018.
  4. Model Projection: Theory and Applications to Fair Machine Learning. In 2020 IEEE International Symposium on Information Theory (ISIT), pp.  2711–2716. IEEE, June 2020. doi: 10.1109/ISIT44484.2020.9173988.
  5. Shun-Ichi Amari. α𝛼\alphaitalic_α -Divergence Is Unique, Belonging to Both f-Divergence and Bregman Divergence Classes. IEEE Transactions on Information Theory, 55(11):4925–4931, November 2009. ISSN 1557-9654. doi: 10.1109/TIT.2009.2030485.
  6. Fairness and Machine Learning: Limitations and Opportunities. fairmlbook.org, 2019. http://www.fairmlbook.org.
  7. AI Fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias, October 2018. URL https://arxiv.org/abs/1810.01943.
  8. Scalable and Stable Surrogates for Flexible Classifiers with Fairness Constraints.
  9. A Convex Framework for Fair Regression, June 2017.
  10. Fairness in criminal justice risk assessments: The state of the art. Sociological Methods & Research, 50(1):3–44, 2021. doi: 10.1177/0049124118782533. URL https://doi.org/10.1177/0049124118782533.
  11. Fairlearn: A toolkit for assessing and improving fairness in AI. Technical Report MSR-TR-2020-32, Microsoft, May 2020. URL https://www.microsoft.com/en-us/research/publication/fairlearn-a-toolkit-for-assessing-and-improving-fairness-in-ai/.
  12. Convex Optimization. Cambridge University Press, Cambridge, UK ; New York, 2004. ISBN 978-0-521-83378-3.
  13. The KL-Divergence Between a Graph Model and its Fair I-Projection as a Fairness Regularizer. In Machine Learning and Knowledge Discovery in Databases, pp.  351–366. Springer International Publishing, 2021.
  14. Optimal Transport of Classifiers to Fairness. Advances in Neural Information Processing Systems, 35:33728–33740, December 2022.
  15. Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees. In Proceedings of the Conference on Fairness, Accountability, and Transparency, pp.  319–328, Atlanta GA USA, January 2019. ACM. ISBN 978-1-4503-6125-5. doi: 10.1145/3287560.3287586.
  16. Alexandra Chouldechova. Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments. Big Data, 5(2):153–163, June 2017. ISSN 2167-6461. doi: 10.1089/big.2016.0047.
  17. FAIR MIXUP: FAIRNESS VIA INTERPOLATION. International Conference on Learning Representations, 2020.
  18. Algorithmic Decision Making and the Cost of Fairness. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’17, pp.  797–806, New York, NY, USA, August 2017. Association for Computing Machinery. ISBN 978-1-4503-4887-4. doi: 10.1145/3097983.3098095.
  19. I. Csiszar. $I$-Divergence Geometry of Probability Distributions and Minimization Problems. The Annals of Probability, 3(1):146–158, 1975. ISSN 0091-1798.
  20. CVXPY: A Python-embedded modeling language for convex optimization. Journal of Machine Learning Research, 17(83):1–5, 2016.
  21. Retiring adult: New datasets for fair machine learning. Advances in Neural Information Processing Systems, 34, 2021.
  22. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, ITCS ’12, pp.  214–226, New York, NY, USA, January 2012. Association for Computing Machinery. ISBN 978-1-4503-1115-1. doi: 10.1145/2090236.2090255.
  23. Algorithmic fairness datasets: The story so far. Data Mining and Knowledge Discovery, 36(6):2074–2152, November 2022. ISSN 1573-756X. doi: 10.1007/s10618-022-00854-z.
  24. Deep fair models for complex data: Graphs labeling and explainable face recognition. Neurocomputing, 470:318–334, 2022. ISSN 0925-2312. doi: https://doi.org/10.1016/j.neucom.2021.05.109. URL https://www.sciencedirect.com/science/article/pii/S0925231221011140.
  25. FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods, June 2023.
  26. Equality of Opportunity in Supervised Learning. In Advances in Neural Information Processing Systems, volume 29. Curran Associates, Inc., 2016.
  27. Anna Lauren Hoffmann. Where fairness fails: Data, algorithms, and the limits of antidiscrimination discourse. Information, Communication & Society, 22(7):900–915, June 2019. ISSN 1369-118X, 1468-4462. doi: 10.1080/1369118X.2019.1573912.
  28. Fairness-Aware Classifier with Prejudice Remover Regularizer. In Peter A. Flach, Tijl De Bie, and Nello Cristianini (eds.), Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science, pp.  35–50, Berlin, Heidelberg, 2012. Springer. ISBN 978-3-642-33486-3. doi: 10.1007/978-3-642-33486-3˙3.
  29. Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness. In Proceedings of the 35th International Conference on Machine Learning, pp.  2564–2572. PMLR, July 2018.
  30. Regularization for Deep Learning: A Taxonomy, October 2017.
  31. Too Relaxed to Be Fair. In Proceedings of the 37th International Conference on Machine Learning, pp.  6360–6369. PMLR, November 2020.
  32. Sode Masashi. Fairtorch. https://github.com/wbawakate/fairtorch, Dec 2020. Version 0.1.2.
  33. Costs and Benefits of Fair Representation Learning. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pp.  263–270, Honolulu HI USA, January 2019. ACM. ISBN 978-1-4503-6324-2. doi: 10.1145/3306618.3317964.
  34. A Survey on Bias and Fairness in Machine Learning. ACM Computing Surveys, 54(6):115:1–115:35, July 2021. ISSN 0360-0300. doi: 10.1145/3457607.
  35. A data-driven approach to predict the success of bank telemarketing. Decision Support Systems, 62:22–31, 2014. ISSN 0167-9236. doi: https://doi.org/10.1016/j.dss.2014.03.001. URL https://www.sciencedirect.com/science/article/pii/S016792361400061X.
  36. Exploiting mmd and sinkhorn divergences for fair and transferable representation learning. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (eds.), Advances in Neural Information Processing Systems, volume 33, pp.  15360–15370. Curran Associates, Inc., 2020. URL https://proceedings.neurips.cc/paper_files/paper/2020/file/af9c0e0c1dee63e5acad8b7ed1a5be96-Paper.pdf.
  37. FNNC: Achieving fairness through neural networks. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI’20, pp.  2277–2283, Yokohama, Yokohama, Japan, January 2021. ISBN 978-0-9992411-6-5.
  38. Addressing fairness in classification with a model-agnostic multi-objective algorithm. In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, pp.  600–609. PMLR, December 2021.
  39. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019.
  40. Fair Kernel Learning. In Michelangelo Ceci, Jaakko Hollmén, Ljupčo Todorovski, Celine Vens, and Sašo Džeroski (eds.), Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science, pp.  339–355, Cham, 2017. Springer International Publishing. ISBN 978-3-319-71249-9. doi: 10.1007/978-3-319-71249-9˙21.
  41. Ellipse area calculations and their applicability in posturography. Gait & Posture, 39(1):518–522, January 2014. ISSN 0966-6362. doi: 10.1016/j.gaitpost.2013.09.001.
  42. Fairness and Abstraction in Sociotechnical Systems. In Proceedings of the Conference on Fairness, Accountability, and Transparency, pp.  59–68, Atlanta GA USA, January 2019. ACM. ISBN 978-1-4503-6125-5. doi: 10.1145/3287560.3287598.
  43. Fairness definitions explained. In Proceedings of the International Workshop on Software Fairness, pp.  1–7, Gothenburg Sweden, May 2018. ACM. ISBN 978-1-4503-5746-3. doi: 10.1145/3194770.3194776.
  44. Why fairness cannot be automated: Bridging the gap between eu non-discrimination law and ai. Computer Law and Security Review 41, (3547922), Mar 2020. doi: 10.2139/ssrn.3547922. URL https://papers.ssrn.com/abstract=3547922.
  45. Optimized Score Transformation for Fair Classification. In Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, pp.  1673–1683. PMLR, June 2020.
  46. Unlocking Fairness: A Trade-off Revisited. In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019.
  47. I-Cheng Yeh and Che hui Lien. The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Systems with Applications, 36(2, Part 1):2473–2480, 2009. ISSN 0957-4174. doi: https://doi.org/10.1016/j.eswa.2007.12.020. URL https://www.sciencedirect.com/science/article/pii/S0957417407006719.
  48. Fairness Constraints: A Flexible Approach for Fair Classification. Journal of Machine Learning Research, 20(75):1–42, 2019. ISSN 1533-7928.
  49. Learning Fair Representations. In Proceedings of the 30th International Conference on Machine Learning, pp.  325–333. PMLR, May 2013.
  50. Mitigating Unwanted Biases with Adversarial Learning. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, AIES ’18, pp.  335–340, New York, NY, USA, December 2018. Association for Computing Machinery. ISBN 978-1-4503-6012-8. doi: 10.1145/3278721.3278779.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free