2000 character limit reached
Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics
Published 9 Nov 2023 in cs.AI | (2311.05227v2)
Abstract: Deontological ethics, specifically understood through Immanuel Kant, provides a moral framework that emphasizes the importance of duties and principles, rather than the consequences of action. Understanding that despite the prominence of deontology, it is currently an overlooked approach in fairness metrics, this paper explores the compatibility of a Kantian deontological framework in fairness metrics, part of the AI alignment field. We revisit Kant's critique of utilitarianism, which is the primary approach in AI fairness metrics and argue that fairness principles should align with the Kantian deontological framework. By integrating Kantian ethics into AI alignment, we not only bring in a widely-accepted prominent moral theory but also strive for a more morally grounded AI landscape that better balances outcomes and procedures in pursuit of fairness and justice.
- A-level results: almost 40% of teacher assessments in england downgraded. The Guardian.
- Fairness and Machine Learning: Limitations and Opportunities. fairmlbook.org. http://www.fairmlbook.org.
- Belz, H. (1991). Equality transformed: A quarter-century of affirmative action, volume 15. Transaction Publishers.
- Benjamin, G. (2022). #fuckthealgorithm: algorithmic imaginaries and political resistance. In FAccT ’22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21 - 24, 2022, pages 46–57. ACM.
- Bentham, J. (1996). The collected works of Jeremy Bentham: An introduction to the principles of morals and legislation. Clarendon Press.
- BGB (2023). German civil code (bürgerliches gesetzbuch - bgb, federal law gazette. Accessed on 2023-10-01.
- Binns, R. (2018). Fairness in machine learning: Lessons from political philosophy. In FAT, volume 81 of Proceedings of Machine Learning Research, pages 149–159. PMLR.
- Burkov, A. (2020). Machine Learning Engineering. Kindle Direct Publishing, 1 edition.
- Disentangling and operationalizing AI fairness at linkedin. In FAccT, pages 1213–1228. ACM.
- Developing a meta-inventory of human values. In ASIST, volume 47 of Proc. Assoc. Inf. Sci. Technol., pages 1–10. Wiley.
- Commission, U. E. E. O. (1964). Title vii of the civil rights act of 1964. Public Law 88-352, 78 Stat. 241, 42 U.S.C. § 2000e et seq.
- Statistical and machine learning models in credit scoring: A systematic literature survey. Appl. Soft Comput., 91:106263.
- Driver, J. (2022). The History of Utilitarianism. In Zalta, E. N. and Nodelman, U., editors, The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, Winter 2022 edition.
- Fairness through awareness. In Goldwasser, S., editor, Innovations in Theoretical Computer Science 2012, Cambridge, MA, USA, January 8-10, 2012, pages 214–226. ACM.
- Studying bias in visual features through the lens of optimal transport. Data Mining and Knowledge Discovery.
- Algorithmic fairness from a non-ideal perspective. In AIES, pages 57–63. ACM.
- Towards a post-market monitoring framework for machine learning-based medical devices: A case study. In NeurIPS 2023 Workshop on Regulatable ML.
- Fredman, S. (2014). Addressing disparate impact: Indirect discrimination and the public sector equality duty. Industrial Law Journal, 43(3):349–363.
- Gabriel, I. (2020). Artificial intelligence, values, and alignment. Minds Mach., 30(3):411–437.
- Gabriel, I. (2022). Toward a theory of justice for artificial intelligence. Daedalus, 151(2):218–231.
- Common errors in statistics (and how to avoid them). John Wiley & Sons.
- Goodin, R. E. (1995). Utilitarianism as a public philosophy. .
- Beyond distributive fairness in algorithmic decision making: Feature selection for procedurally fair learning. In AAAI, pages 51–60. AAAI Press.
- Equality of opportunity in supervised learning. In NIPS, pages 3315–3323.
- “the algorithm will screw you”: Blame, social actors and the 2020 a level results algorithm on twitter. Plos one, 18(7):e0288662.
- A moral framework for understanding fair ML through economic models of equality of opportunity. In danah boyd and Morgenstern, J. H., editors, Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* 2019, Atlanta, GA, USA, January 29-31, 2019, pages 181–190. ACM.
- Affirmative algorithms: The legal grounds for fairness as awareness. U. Chi. L. Rev. Online, page 134.
- Huyen, C. (2022). Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications. O’Reilly.
- Fairness-aware classifier with prejudice remover regularizer. In ECML/PKDD (2), volume 7524 of Lecture Notes in Computer Science, pages 35–50. Springer.
- Kant, I. (1785). Groundwork of the Metaphysics of Morals. Cambridge University Press.
- Groundwork of the metaphysics of morals: Practical philosophy. Trans MJ Gregor (Cambridge University Press, Cambridge, 1996), 4(456):p102.
- Kim, P. T. (2022). Race-aware algorithms: Fairness, nondiscrimination and affirmative action. California Law Review, 110.
- Knutsson, S. (2016). Measuring happiness and suffering. Foundational Research Institute.
- Kolkman, D. (2020). F** k the algorithm?: what the world can learn from the uk’s a-level grading fiasco. Impact of Social Sciences Blog.
- Korsgaard, C. M. (1996). The sources of normativity. Cambridge University Press.
- Korsgaard, C. M. (2018). Fellow creatures: Our obligations to the other animals. Oxford University Press.
- Counterfactual fairness. In NIPS, pages 4066–4076.
- KWG (2023). Banking act (kreditwesengesetz - kwg), bundesministerium für justiz. Accessed on 2023-10-01.
- Kymlicka, W. (2002). Contemporary political philosophy: An introduction. oxford: oxford University Press.
- Beneficent intelligence: A capability approach to modeling benefit, assistance, and associated moral failures through ai systems.
- Macleod, C. (2020). John Stuart Mill. In Zalta, E. N., editor, The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, Summer 2020 edition.
- Implications of AI (un-)fairness in higher education admissions: the effects of perceived AI (un-)fairness on exit, voice and organizational reputation. In FAT*, pages 122–130. ACM.
- The secret bias hidden in mortgage-approval algorithms. The Markup.
- Minimax pareto fairness: A multi objective perspective. In III, H. D. and Singh, A., editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 6755–6764. PMLR.
- The cost of fairness in binary classification. In FAT, volume 81 of Proceedings of Machine Learning Research, pages 107–118. PMLR.
- Mill, J. S. (1966). Utilitarianism. Springer.
- Bias in data-driven artificial intelligence systems - an introductory survey. WIREs Data Mining Knowl. Discov., 10(3).
- O’Neill, O. (2022). A philosopher looks at digital communication, volume 4. Cambridge University Press.
- Necessity of processing sensitive data for bias detection and monitoring: A techno-legal exploration. In NeurIPS 2023 Workshop on Regulatable ML.
- Causal inference in statistics: A primer. John Wiley & Sons.
- Discrimination-aware data mining. In KDD, pages 560–568. ACM.
- Programming machine ethics, volume 26. Springer.
- Post-processing for individual fairness. In NeurIPS, pages 25944–25955.
- Posner, R. A. (1979). Utilitarianism, economics, and legal theory. The Journal of Legal Studies, 8(1):103–140.
- The use of responsible artificial intelligence techniques in the context of loan approval processes. Int. J. Hum. Comput. Interact., 39(7):1543–1562.
- Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy. Nat. Mach. Intell., 3(10):896–904.
- Can we trust fair-ai? In AAAI, pages 15421–15430. AAAI Press.
- Encoding ethics to compute value-aligned norms. Minds & Machines.
- Machine learning and the meaning of equal treatment. In Fourcade, M., Kuipers, B., Lazar, S., and Mulligan, D. K., editors, AIES ’21: AAAI/ACM Conference on AI, Ethics, and Society, Virtual Event, USA, May 19-21, 2021, pages 956–966. ACM.
- Singer, P. (2011). Practical Ethics. Cambridge University Press, 3rd edition.
- Utilitarianism: For and against. Cambridge University Press.
- Ethics, technology, and engineering: An introduction. John Wiley & Sons.
- Algorithmic auditing and social justice: Lessons from the history of audit studies. In Equity and Access in Algorithms, Mechanisms, and Optimization, pages 1–9. EEAMO’21.
- Bias preservation in machine learning: The legality of fairness metrics under eu non-discrimination law. West Virginia Law Review, 123(3).
- Why fairness cannot be automated: Bridging the gap between eu non-discrimination law and ai. Computer Law & Security Review, 41:105567.
- Moral machines: Teaching robots right from wrong. Oxford University Press.
- Watson, L. (2021). The right to know: Epistemic rights and why we need them. Routledge.
- Fairness constraints: Mechanisms for fair classification. In AISTATS, volume 54 of Proceedings of Machine Learning Research, pages 962–970. PMLR.
- Fairness constraints: A flexible approach for fair classification. J. Mach. Learn. Res., 20:75:1–75:42.
Paper Prompts
Sign up for free to create and run prompts on this paper.