SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
This work addresses fairness in machine learning for applications susceptible to bias, presenting an incremental improvement over existing methods.
The paper tackles the problem of algorithmic bias by proposing a method to enforce individual fairness through invariance on sensitive sets, resulting in improved fairness metrics compared to recent fair training procedures across three machine learning tasks.
In this paper, we cast fair machine learning as invariant machine learning. We first formulate a version of individual fairness that enforces invariance on certain sensitive sets. We then design a transport-based regularizer that enforces this version of individual fairness and develop an algorithm to minimize the regularizer efficiently. Our theoretical results guarantee the proposed approach trains certifiably fair ML models. Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are susceptible to algorithmic bias.