论文标题
以改善为重点的因果追索权（ICR）
Improvement-Focused Causal Recourse (ICR)
论文作者
论文摘要
算法追索性建议，例如Karimi等人（2021年）因果关系（CR），告知利益相关者如何采取行动以恢复不利的决定。但是，某些行动会导致接受（即，恢复模型的决定），但不会导致改进（即可能不会恢复基本的现实状态）。建议这样的行动是建议欺骗预测因子。我们引入了一种新颖的方法，以改进为重点的因果追索权（ICR），其中涉及概念上的转变：首先，我们需要ICR建议来指导改进。其次，我们不量身定制建议被特定的预测指标接受。取而代之的是，我们利用因果知识来设计准确预测恢复前后的决策系统。结果，改进保证可以转化为接受保证。我们证明，鉴于正确的因果知识，ICR与现有方法相反，指导接受和改善。
Algorithmic recourse recommendations, such as Karimi et al.'s (2021) causal recourse (CR), inform stakeholders of how to act to revert unfavourable decisions. However, some actions lead to acceptance (i.e., revert the model's decision) but do not lead to improvement (i.e., may not revert the underlying real-world state). To recommend such actions is to recommend fooling the predictor. We introduce a novel method, Improvement-Focused Causal Recourse (ICR), which involves a conceptual shift: Firstly, we require ICR recommendations to guide towards improvement. Secondly, we do not tailor the recommendations to be accepted by a specific predictor. Instead, we leverage causal knowledge to design decision systems that predict accurately pre- and post-recourse. As a result, improvement guarantees translate into acceptance guarantees. We demonstrate that given correct causal knowledge, ICR, in contrast to existing approaches, guides towards both acceptance and improvement.
