Algorithmic Decision Making with Conditional Fairness

Abstract

Nowadays fairness issues have raised great concerns in decision-making systems. Various fairness notions have been proposed to measure the degree to which an algorithm is unfair. In practice, there frequently exist a certain set of variables we term as fair variables, which are pre-decision covariates such as users' choices. The effects of fair variables are irrelevant in assessing the fairness of the decision support algorithm. We thus define conditional fairness as a more sound fairness metric by conditioning on the fairness variables. Given different prior knowledge of fair variables, we demonstrate that traditional fairness notations, such as demographic parity and equalized odds, are special cases of our conditional fairness notations. Moreover, we propose a Derivable Conditional Fairness Regularizer (DCFR), which can be integrated into any decision-making model, to track the trade-off between precision and fairness of algorithmic decision making. Specifically, an adversarial representation based conditional independence loss is proposed in our DCFR to measure the degree of unfairness. With extensive experiments on three real-world datasets, we demonstrate the advantages of our conditional fairness notation and DCFR.

arXiv commentKDD 2020

References in corpus (11)

• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• Fairness Without Demographics in Repeated Loss Minimization
• Censoring Representations with an Adversary
• PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
• A Scalable Conditional Independence Test for Nonlinear, Non-Gaussian Data
• Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions

Cited by in corpus (8)

• Towards Out-Of-Distribution Generalization: A Survey
• Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey
• A survey on datasets for fairness-aware machine learning
• Training Fair Models in Federated Learning without Data Privacy Infringement
• Regulatory Instruments for Fair Personalized Pricing
• Formalising Anti-Discrimination Law in Automated Decision Systems
• Algorithmic Fairness Datasets: the Story so Far
• A Sociotechnical View of Algorithmic Fairness