论文标题
Sensei：敏感的设置不变性，以实现个人公平
SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
论文作者
论文摘要
在本文中，我们将公平的机器学习作为不变的机器学习。我们首先制定一个个人公平的版本，该版本可以在某些敏感的集合上实现不变性。然后，我们设计了一个基于运输的正规器，该规则可以强制执行此版本的个人公平性，并开发出一种算法以有效地最大程度地减少正规器。我们的理论结果保证了拟议的方法训练公平的ML模型。最后，在实验研究中，我们证明了公平度指标的改善，与最近对三个ML任务易受算法偏见感染的公平培训程序相比。
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.
