Counterfactual Fairness Through Transforming Data Orthogonal to Bias

Machine learning models have demonstrated exceptional capabilities in solving complex problems across a variety of domains. However, these models can sometimes exhibit biased decision-making, leading to unequal treatment of different groups. Despite substantial research on counterfactual fairness, existing methods remain underdeveloped in addressing the impact of multivariate and continuous sensitive variables on decision-making outcomes. To tackle this gap, we propose a novel data pre-processing algorithm, Orthogonal to Bias (OB), which is designed to eliminate the influence of a group of continuous sensitive variables, thereby promoting counterfactual fairness in machine learning applications. Our approach, based on the assumption of an elliptical distribution within a structural causal model (SCM), shows that counterfactual fairness can be achieved by ensuring the data is orthogonal to the observed sensitive variables. The OB algorithm is model-agnostic, making it applicable to a wide range of machine learning models and tasks. To enhance numerical stability, we also introduce a sparse variant that incorporates regularization. Empirical evaluations on both simulated and real-world datasets-spanning scenarios with both discrete and continuous sensitive variables-demonstrate that our method effectively promotes fairer outcomes without compromising predictive accuracy.