A recourse action aims to explain a particular algorithmic decision by showing one specific way in which the instance could be modified to receive an alternate outcome. Existing recourse generation methods often assume that the machine learning model does not change over time. However, this assumption does not always hold in practice because of data distribution shifts, and in this case, the recourse action may become invalid. To redress this shortcoming, we propose the Distributionally Robust Recourse Action (DiRRAc) framework, which generates a recourse action that has a high probability of being valid under a mixture of model shifts. We formulate the robustified recourse setup as a min-max optimization problem, where the max problem is specified by Gelbrich distance over an ambiguity set around the distribution of model parameters. Then we suggest a projected gradient descent algorithm to find a robust recourse according to the min-max objective. We show that our DiRRAc framework can be extended to hedge against the misspecification of the mixture weights. Numerical experiments with both synthetic and three real-world datasets demonstrate the benefits of our proposed framework over state-of-the-art recourse methods.

翻译：反事实解释行动旨在通过展示实例可被修改以获得替代结果的具体方式，来解释特定算法决策。现有解释生成方法通常假设机器学习模型不会随时间变化。然而，由于数据分布偏移，这一假设在实践中并不总是成立，此时反事实解释行动可能失效。为弥补这一缺陷，我们提出了分布鲁棒反事实解释行动（DiRRAc）框架，该框架能在模型偏移的混合分布下生成具有高有效概率的解释行动。我们将鲁棒化解释设定建模为极小极大优化问题，其中极大化问题通过围绕模型参数分布模糊集的Gelbrich距离来定义。随后，我们提出一种投影梯度下降算法，根据极小极大目标寻找鲁棒解释。研究表明，我们的DiRRAc框架可扩展至防范混合权重设定错误的风险。基于合成数据集与三个真实数据集的数值实验表明，所提框架的性能优于现有最优解释方法。