论文信息 - Inherent Trade-Offs in Algorithmic Fairness

Inherent Trade-Offs in Algorithmic Fairness

Recent discussion in both the academic literature and the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups. We consider several of the key fairness conditions that lie at the heart of these debates, and discuss recent research establishing inherent trade-offs between these conditions. We also consider a variety of methods for promoting fairness and related notions for classification and selection problems that involve sets rather than just individuals.

Jon M. Kleinberg | J. Kleinberg

[1] Nathan Srebro,et al. Equality of Opportunity in Supervised Learning , 2016, NIPS.

[2] Carlos Eduardo Scheidegger,et al. Certifying and Removing Disparate Impact , 2014, KDD.

[3] Toniann Pitassi,et al. Fairness through awareness , 2011, ITCS '12.

[4] Christopher T. Lowenkamp,et al. False Positives, False Negatives, and False Analyses: A Rejoinder to "Machine Bias: There's Software Used across the Country to Predict Future Criminals. and It's Biased against Blacks" , 2016 .

[5] W. Heath. The Difference: How the Power of Diversity Creates Better Groups, Firms, Schools, and Societies , 2008 .

[6] Jon M. Kleinberg,et al. On Fairness and Calibration , 2017, NIPS.

[7] Alexandra Chouldechova,et al. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments , 2016, Big Data.

[8] Jon M. Kleinberg,et al. Inherent Trade-Offs in the Fair Determination of Risk Scores , 2016, ITCS.

[9] Jon M. Kleinberg,et al. Selection Problems in the Presence of Implicit Bias , 2018, ITCS.

[10] Jon M. Kleinberg,et al. Team Performance with Test Scores , 2018, TEAC.

[11] Avi Feller,et al. Algorithmic Decision Making and the Cost of Fairness , 2017, KDD.

[12] Lu Hong,et al. Groups of diverse problem solvers can outperform groups of high-ability problem solvers. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[13] Andrew D. Selbst,et al. Big Data's Disparate Impact , 2016 .