Ashrya Agrawal, Florian Pfisterer, Bernd Bischl, Francois Buet-Golfouse, Srijan Sood, Jiahao Chen, Sameena Shah, Sebastian Vollmer
arXiv 4 Nov 2020 · Machine Learning · 4 citations (OpenAlex)
arXiv:2011.02407 · PDF · DOI · OpenAlex · Extracted main text
We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse rather than better. A rigorous evaluation of the debiasing treatment effect requires extensive cross-validation beyond what is usually done. We demonstrate that this phenomenon can be explained as a consequence of bias-variance trade-off, with an increase in variance necessitated by imposing a fairness constraint. Follow-up experiments validate the theoretical prediction that the estimation variance depends strongly on the base rates of the protected class. Considering fairness--performance trade-offs justifies the counterintuitive notion that partial debiasing can actually yield better results in practice on out-of-sample data.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | J. S. Kim, J. Chen, and A. Talwalkar (2020) Model-agnostic characterization of fairness trade-offs | 1.000 | 5 | 3 | 100% |
| 2 | R. K. E. Bellamy, K. Dey, M. Hind, S. C. Hoffman, S. Houde, K. Kanna… (2019) AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias | 0.737 | 3 | 2 | 100% |
| 3 | J. Angwin, J. Larson, S. Mattu, and L. Kichner (2016) Machine bias, May 2016 | 0.737 | 3 | 2 | 100% |
| 4 | D. Dua and C. Graff (2017) UCI machine learning repository, 2017 | 0.693 | 6 | 1 | 100% |
| 5 | M. Hardt, E. Price, and N. Srebro (2016) Equality of opportunity in supervised learning | 0.644 | 4 | 1 | 100% |
| 6 | A. Chouldechova (2016) Fair prediction with disparate impact: A study of bias in recidivism prediction instruments | 0.644 | 4 | 1 | 100% |
| 7 | R. Berk, H. Heidari, S. Jabbari, M. Kearns, and A. Roth (2018) Fairness in criminal justice risk assessments: The state of the art | 0.644 | 4 | 1 | 100% |
| 8 | S. A. Friedler, C. Scheidegger, S. Venkatasubramanian, S. Choudhary,… (2019) A comparative study of fairness-enhancing interventions in machine learning | 0.644 | 2 | 2 | 100% |
| 9 | P. Saleiro, B. Kuester, A. Stevens, A. Anisfeld, L. Hinkson, J. Lond… (1811) Aequitas: A bias and fairness audit toolkit, 2018 | 0.644 | 2 | 2 | 100% |
| 10 | S. Barocas and A. Selbst (2016) Big data's disparate impact | 0.511 | 2 | 1 | 100% |
Showing the top 10 of 54 scored citations.