EconBase
← All papers

Debiasing classifiers: is reality at variance with expectation?

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

Abstract

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.

Citation extraction

54
references
87
in-text mentions
54
distinct cited
0
self-citations
6,978
main-text words

appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.

Most heavily cited references

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.

ReferenceIntensityMentionsSectionsMain text
1J. S. Kim, J. Chen, and A. Talwalkar (2020) Model-agnostic characterization of fairness trade-offs1.00053100%
2R. 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 bias0.73732100%
3J. Angwin, J. Larson, S. Mattu, and L. Kichner (2016) Machine bias, May 20160.73732100%
4D. Dua and C. Graff (2017) UCI machine learning repository, 20170.69361100%
5M. Hardt, E. Price, and N. Srebro (2016) Equality of opportunity in supervised learning0.64441100%
6A. Chouldechova (2016) Fair prediction with disparate impact: A study of bias in recidivism prediction instruments0.64441100%
7R. Berk, H. Heidari, S. Jabbari, M. Kearns, and A. Roth (2018) Fairness in criminal justice risk assessments: The state of the art0.64441100%
8S. A. Friedler, C. Scheidegger, S. Venkatasubramanian, S. Choudhary,… (2019) A comparative study of fairness-enhancing interventions in machine learning0.64422100%
9P. Saleiro, B. Kuester, A. Stevens, A. Anisfeld, L. Hinkson, J. Lond… (1811) Aequitas: A bias and fairness audit toolkit, 20180.64422100%
10S. Barocas and A. Selbst (2016) Big data's disparate impact0.51121100%

Showing the top 10 of 54 scored citations.