论文标题
反事实公平：通过正规化消除直接效果
Counterfactual fairness: removing direct effects through regularization
论文作者
论文摘要
建立相对于一个无私的组公平的机器学习模型是一个局部问题。现代公平感知算法通常通过仅适用于机器学习模型的一部分的修改来忽略因果效应和实施公平性。在这项工作中，我们提出了一个新的公平定义，该定义通过受控直接效应（CDE）结合了因果关系。我们开发正规化来解决古典公平措施，并提出一个因果正规化，该因素通过消除了CDE衡量的模型结果的影响来满足我们的新公平定义。这些正规化适用于通过迭代通过差异来最大程度地降低损失的任何模型。我们使用梯度提升和逻辑回归在：合成数据集，UCI成人（人口普查）数据集和现实世界中的信用风险数据集上演示了我们的方法。发现我们的结果可以减轻预测的不公平性，而模型性能的降低却很小。
Building machine learning models that are fair with respect to an unprivileged group is a topical problem. Modern fairness-aware algorithms often ignore causal effects and enforce fairness through modifications applicable to only a subset of machine learning models. In this work, we propose a new definition of fairness that incorporates causality through the Controlled Direct Effect (CDE). We develop regularizations to tackle classical fairness measures and present a causal regularization that satisfies our new fairness definition by removing the impact of unprivileged group variables on the model outcomes as measured by the CDE. These regularizations are applicable to any model trained using by iteratively minimizing a loss through differentiation. We demonstrate our approaches using both gradient boosting and logistic regression on: a synthetic dataset, the UCI Adult (Census) Dataset, and a real-world credit-risk dataset. Our results were found to mitigate unfairness from the predictions with small reductions in model performance.
