On Learning and Testing Counterfactual Fairness in Machine Learning

Professor Wenbin Lu

NC State University
Barton Lectures in Computational Mathematics


Date: Wednesday, February 10, 2021
Time: 4:00 pm - 5:00 pm
Location: Virtual

Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly. Recent work brings the discussion of machine learning fairness into the causal framework and elaborates on the concept of Counterfactual Fairness. In this work, we develop the Fair Learning through dAta Preprocessing (FLAP) algorithm to learn counterfactually fair decisions from biased training data and formalize the conditions where different data preprocessing procedures should be used to guarantee counterfactual fairness. We also show that Counterfactual Fairness is equivalent to the conditional independence of the decisions and the sensitive attributes given the processed non-sensitive attributes, which enables us to detect discrimination in the original decision using the processed data. The performance of our algorithm is illustrated using simulated data and a real-world application in loan assessment.