Training individually fair ML models with sensitive subspace robustness
ICLR(2020)
摘要
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.
更多查看译文
关键词
fairness, adversarial robustness
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络