Training individually fair ML models with sensitive subspace robustness

Mikhail Yurochkin, Amanda Bower, Yuekai Sun

Keywords: adversarial, fairness, optimization, perturbation, robustness

Thursday: Fairness, Interpretabiity and Deployment

Abstract: We consider training machine learning models that are fair in the sense that their performance is invariant under certain sensitive perturbations to the inputs. For example, the performance of a resume screening system should be invariant under changes to the gender and/or ethnicity of the applicant. We formalize this notion of algorithmic fairness as a variant of individual fairness and develop a distributionally robust optimization approach to enforce it during training. We also demonstrate the effectiveness of the approach on two ML tasks that are susceptible to gender and racial biases.

Similar Papers

Rényi Fair Inference
Sina Baharlouei, Maher Nouiehed, Ahmad Beirami, Meisam Razaviyayn,
Conditional Learning of Fair Representations
Han Zhao, Amanda Coston, Tameem Adel, Geoffrey J. Gordon,