On Learning and Testing of Counterfactual Fairness through Data Preprocessing
This work addresses fairness concerns in decision-making systems, offering a method to mitigate bias, though it appears incremental by building on existing causal fairness frameworks.
The paper tackles the problem of ensuring counterfactual fairness in machine learning decisions from biased data by developing the FLAP algorithm and formalizing conditions for data preprocessing, with performance demonstrated on simulated and real-world data.
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 paper, 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 real-world applications.