RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity
This addresses fairness in machine learning by providing a method to generate bias-free data for detecting unfairness, though it is incremental as it builds on existing BN frameworks.
The paper tackles the problem of encoding Rawlsian fair equality of opportunity (FEO) into Bayesian Network models to generate aspirational data distributions that reflect an ideally fair society, resulting in a system called RAWLSNET that alters BN parameters to satisfy or minimize deviation from FEO.
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.