A General Approach to Fairness with Optimal Transport

By Silvia Chiappa, Ray Jiang, T. Stepleton, Aldo Pacchiano, Heinrich Jiang, John Aslanides. 2020

97 citations recorded by the source corpus.

We propose a general approach to fairness based on transporting distributions corresponding to different sensitive attributes to a common distribution. We use optimal transport theory to derive target distributions and methods that allow us to achieve fairness with minimal changes to the unfair model. Our approach is applicable to both classification and regression problems, can enforce different notions of fairness, and enable us to achieve a Pareto-optimal trade-off between accuracy and fairness. We demonstrate that it outperforms previous approaches in several benchmark fairness datasets.

Subfields: Safety Research, AI Ethics, Fairness & Society, Mathematical Optimization

Citations in the corpus

• Reducing Sentiment Bias in Language Models via Counterfactual Evaluation (2019, neutral): “diction outputs (Calders et al., 2009; Zhang et al., 2018; Jiang et al., 2019; Chiappa et al., 2020).”