A General Approach to Fairness with Optimal Transport

  • Chiappa Silvia DeepMind London
  • Jiang Ray DeepMind London
  • Stepleton Tom DeepMind London
  • Pacchiano Aldo UC Berkeley
  • Jiang Heinrich Google Research
  • Aslanides John DeepMind London


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.

AAAI Technical Track: Machine Learning