Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction

By Christina Wadsworth, Francesca Vera, C. Piech. 2018

197 citations recorded by the source corpus.

Recidivism prediction scores are used across the USA to determine sentencing and supervision for hundreds of thousands of inmates. One such generator of recidivism prediction scores is Northpointe's Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) score, used in states like California and Florida, which past research has shown to be biased against black inmates according to certain measures of fairness. To counteract this racial bias, we present an adversarially-trained neural network that predicts recidivism and is trained to remove racial bias. When comparing the results of our model to COMPAS, we gain predictive accuracy and get closer to achieving two out of three measures of fairness: parity and equality of odds. Our model can be generalized to any prediction and demographic. This piece of research contributes an example of scientific replication and simplification in a high-stakes real-world application like recidivism prediction.

Subfields: Artificial Intelligence, Safety Research, Sociology and Political Science, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In Sociology and Political Science

In AI Ethics, Fairness & Society

Citations in the corpus

Fair-by-design explainable models for prediction of recidivism (2019, background): “In each of these cases, a high-risk misclassiﬁcation may negatively impact on a criminal defendant’s outcome [3, 4].”
Algorithmic Fairness (2020, methodology): “In one approach, it was suggested to use the feedback structure to check whether a trained classifier is fair or not and then update the model accordingly [32, 137, 145].”
An adversarial approach for the robust classification of pneumonia from chest radiographs (2020, background): “For example, there is a significant body of literature in the area of algorithmic fairness where adversarial training has been used to learn representations that are fair with respect to protected classes such as race or gender [4, 18, 37].”
Federated Adversarial Debiasing for Fair and Transferable Representations (2021, unknown): “Related central algorithms have been exploited [8, 29, 45].”
A Review on Fairness in Machine Learning (2022, methodology): “In one approach, it was suggested to use the feedback structure to check whether a trained classifier is fair or not and then update the model accordingly [40, 207, 219].”
Fairness in Machine Learning: A Survey (2020, background): “Most approaches in this area use notions of fairness within the adversary to apply feedback for model tuning as a form of in-processing, where the adversary penalizes the model if a sensitive variable is predictable from the dependent variable (e.g., References [28, 30, 58, 91, 289, 299, 305, 314]).”