RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity

12 Pages Posted: 1 Apr 2021

See all articles by David M. Liu

David M. Liu

Northeastern University

Zohair Shafi

Northeastern University

Will Fleisher

Northeastern University

Tina Eliassi-Rad

Northeastern University

Scott Alfeld

affiliation not provided to SSRN

Date Written: January 31, 2021

Abstract

We present RAWLSNET, a system for altering Bayesian Network (BN) models to satisfy the Rawlsian principle of fair equality of opportunity (FEO). RAWLSNET's BN models generate aspirational data distributions: data generated to reflect an ideally fair, FEO-satisfying society. FEO states that everyone with the same talent and willingness to use it should have the same chance of achieving advantageous social positions (e.g., employment), regardless of their background circumstances (e.g., socioeconomic status). Satisfying FEO requires alterations to social structures such as school assignments. Our paper describes RAWLSNET, a method which takes as input a BN representation of an FEO application and alters the BN's parameters so as to satisfy FEO when possible, and minimize deviation from FEO otherwise. We also offer guidance for applying RAWLSNET, including on recognizing proper applications of FEO. We demonstrate the use of our system with publicly available data sets. RAWLSNET's altered BNs offer the novel capability of generating aspirational data for FEO-relevant tasks. Aspirational data are free from the biases of real-world data, and thus are useful for recognizing and detecting sources of unfairness in machine learning algorithms besides biased data.

Keywords: Rawlsian Fair equality of opportunity, Bayesian Networks, Aspirational Data

Suggested Citation

Liu, David and Shafi, Zohair and Fleisher, Will and Eliassi-Rad, Tina and Alfeld, Scott, RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity (January 31, 2021). Available at SSRN: https://ssrn.com/abstract=3816196 or http://dx.doi.org/10.2139/ssrn.3816196

David Liu

Northeastern University ( email )

177 Huntington Ave
Boston, MA 02115
United States

HOME PAGE: http://dliu18.github.io

Zohair Shafi

Northeastern University ( email )

360 Huntington Avenue
Boston, MA 02115
United States

Will Fleisher

Northeastern University ( email )

220 B RP
Boston, MA 02115
United States

Tina Eliassi-Rad (Contact Author)

Northeastern University ( email )

360 Huntington Ave, Mailstop 1010-177
Boston, MA 02115
United States

Scott Alfeld

affiliation not provided to SSRN

Do you want regular updates from SSRN on Twitter?

Paper statistics

Downloads
39
Abstract Views
303
PlumX Metrics