Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Standardizing AI Bias Exploration (2405.19022v1)

Published 29 May 2024 in cs.LG, cs.CY, and cs.HC

Abstract: Creating fair AI systems is a complex problem that involves the assessment of context-dependent bias concerns. Existing research and programming libraries express specific concerns as measures of bias that they aim to constrain or mitigate. In practice, one should explore a wide variety of (sometimes incompatible) measures before deciding which ones warrant corrective action, but their narrow scope means that most new situations can only be examined after devising new measures. In this work, we present a mathematical framework that distils literature measures of bias into building blocks, hereby facilitating new combinations to cover a wide range of fairness concerns, such as classification or recommendation differences across multiple multi-value sensitive attributes (e.g., many genders and races, and their intersections). We show how this framework generalizes existing concepts and present frequently used blocks. We provide an open-source implementation of our framework as a Python library, called FairBench, that facilitates systematic and extensible exploration of potential bias concerns.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. An intersectional definition of fairness, in: 2020 IEEE 36th International Conference on Data Engineering (ICDE), IEEE, 2020, pp. 1918–1921.
  2. N. AI, Artificial intelligence risk management framework (ai rmf 1.0) (2023).
  3. Trustworthy ai: From principles to practices, ACM Computing Surveys 55 (2023) 1–46.
  4. Bias in data-driven artificial intelligence systems—an introductory survey, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 10 (2020) e1356.
  5. Algorithmic fairness: Choices, assumptions, and definitions, Annual Review of Statistics and Its Application 8 (2021) 141–163.
  6. A survey on bias and fairness in machine learning, ACM computing surveys (CSUR) 54 (2021) 1–35.
  7. Fairness through awareness, in: Proceedings of the 3rd innovations in theoretical computer science conference, 2012, pp. 214–226.
  8. Counterfactual fairness, Advances in neural information processing systems 30 (2017).
  9. A. N. Carey, X. Wu, The causal fairness field guide: Perspectives from social and formal sciences, Frontiers in Big Data 5 (2022) 892837.
  10. L. Rosenblatt, R. T. Witter, Counterfactual fairness is basically demographic parity, in: Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, 2023, pp. 14461–14469.
  11. V. Xinying Chen, J. Hooker, A guide to formulating fairness in an optimization model, Annals of Operations Research (2023) 1–39.
  12. Inherent trade-offs in the fair determination of risk scores, arXiv preprint arXiv:1609.05807 (2016).
  13. T. Miconi, The impossibility of" fairness": a generalized impossibility result for decisions, arXiv preprint arXiv:1707.01195 (2017).
  14. Ai fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias, IBM Journal of Research and Development 63 (2019) 4–1.
  15. Fairlearn: A toolkit for assessing and improving fairness in ai, Microsoft, Tech. Rep. MSR-TR-2020-32 (2020).
  16. The what-if tool: Interactive probing of machine learning models, IEEE transactions on visualization and computer graphics 26 (2019) 56–65.
  17. Aequitas: A bias and fairness audit toolkit, arXiv preprint arXiv:1811.05577 (2018).
  18. The zoo of fairness metrics in machine learning (2021).
  19. T. Calders, S. Verwer, Three naive bayes approaches for discrimination-free classification, Data mining and knowledge discovery 21 (2010) 277–292.
  20. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment, in: Proceedings of the 26th international conference on world wide web, 2017, pp. 1171–1180.
  21. Multi-dimensional discrimination in law and machine learning-a comparative overview, in: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023, pp. 89–100.
  22. Equality of opportunity in supervised learning, Advances in neural information processing systems 29 (2016).
  23. Empirical risk minimization under fairness constraints, Advances in neural information processing systems 31 (2018).
  24. Fairness-aware pagerank, in: Proceedings of the Web Conference 2021, 2021, pp. 3815–3826.
  25. Controlling attribute effect in linear regression, in: 2013 IEEE 13th international conference on data mining, IEEE, 2013, pp. 71–80.
  26. Evaluating the fairness of predictive student models through slicing analysis, in: Proceedings of the 9th international conference on learning analytics & knowledge, 2019, pp. 225–234.
  27. Characterizing intersectional group fairness with worst-case comparisons, in: Artificial Intelligence Diversity, Belonging, Equity, and Inclusion, PMLR, 2021, pp. 22–34.
  28. Preventing fairness gerrymandering: Auditing and learning for subgroup fairness, in: International conference on machine learning, PMLR, 2018, pp. 2564–2572.
  29. An empirical study of rich subgroup fairness for machine learning, in: Proceedings of the conference on fairness, accountability, and transparency, 2019, pp. 100–109.
  30. Subgroup generalization and fairness of graph neural networks, Advances in Neural Information Processing Systems 34 (2021) 1048–1061.
  31. Blind pareto fairness and subgroup robustness, in: International Conference on Machine Learning, PMLR, 2021, pp. 7492–7501.
  32. On learning fairness and accuracy on multiple subgroups, Advances in Neural Information Processing Systems 35 (2022) 34121–34135.
  33. Preference-informed fairness, arXiv preprint arXiv:1904.01793 (2019).
  34. Fairness in ranking: A survey, arXiv preprint arXiv:2103.14000 (2021).
  35. Fairness in rankings and recommendations: an overview, The VLDB Journal (2022) 1–28.
  36. The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness, arXiv preprint arXiv:2202.09519 (2022).
  37. Flac: Fairness-aware representation learning by suppressing attribute-class associations, arXiv preprint arXiv:2304.14252 (2023).
  38. E. Krasanakis, A. L. Symeonidis, Forward oriented programming: A meta-dsl for fast development of component libraries, Available at SSRN 4180025 (????).
  39. W. McKinney, et al., pandas: a foundational python library for data analysis and statistics, Python for high performance and scientific computing 14 (2011) 1–9.
  40. Array programming with numpy, Nature 585 (2020) 357–362.
  41. Pytorch: An imperative style, high-performance deep learning library, Advances in neural information processing systems 32 (2019).
  42. Tensorflow: Large-scale machine learning on heterogeneous distributed systems, arXiv preprint arXiv:1603.04467 (2016).
  43. Eagerpy: Writing code that works natively with pytorch, tensorflow, jax, and numpy, arXiv preprint arXiv:2008.04175 (2020).
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now