🤖 AI Summary
Machine learning models often exhibit counterfactual unfairness due to multiple continuous sensitive attributes (e.g., age, income). To address this, we propose Orthogonalization to Bias (OB), a preprocessing algorithm grounded in structural causal models (SCMs) and the joint normality assumption. We formally prove—first in the literature—that linearly projecting features onto the subspace orthogonal to sensitive variables guarantees strict counterfactual fairness. OB constitutes a model-agnostic preprocessing framework compatible with both continuous and discrete sensitive attributes, enhanced by sparse regularization to improve numerical stability. Extensive experiments on synthetic and real-world datasets demonstrate that OB reduces the Counterfactual Fairness Distance (CFD) by 42% while preserving predictive accuracy across diverse models, thereby validating its generalizability and practical efficacy.
📝 Abstract
Machine learning models have shown exceptional prowess in solving complex issues across various domains. However, these models can sometimes exhibit biased decision-making, resulting in unequal treatment of different groups. Despite substantial research on counterfactual fairness, methods to reduce the impact of multivariate and continuous sensitive variables on decision-making outcomes are still underdeveloped. 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, thus promoting counterfactual fairness in machine learning applications. Our approach, based on the assumption of a jointly normal distribution within a structural causal model (SCM), demonstrates 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. Additionally, it includes a sparse variant to improve numerical stability through regularization. Empirical evaluations on both simulated and real-world datasets, encompassing settings with both discrete and continuous sensitive variables, show that our methodology effectively promotes fairer outcomes without compromising accuracy.