[论文解读] Algorithmic Recourse: from Counterfactual Explanations to Interventions

Amir-Hossein Karimi, Bernhard Schölkopf+1 more|arXiv (Cornell University)|Feb 14, 2020

Explainable Artificial Intelligence (XAI)参考文献 50被引用 72

一句话总结

本文认为仅凭反事实解释不足以实现可操作的追索，并引入使用因果模型的最小干预框架（MINT），以提供成本高效、可行的能够改变预测结果的行动。它展示了通过最小干预的追索在合成数据和现实世界场景中可以优于传统基于反事实解释的追索。

ABSTRACT

As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. Counterfactual explanations -- "how the world would have (had) to be different for a desirable outcome to occur" -- aim to satisfy these criteria. Existing works have primarily focused on designing algorithms to obtain counterfactual explanations for a wide range of settings. However, one of the main objectives of "explanations as a means to help a data-subject act rather than merely understand" has been overlooked. In layman's terms, counterfactual explanations inform an individual where they need to get to, but not how to get there. In this work, we rely on causal reasoning to caution against the use of counterfactual explanations as a recommendable set of actions for recourse. Instead, we propose a shift of paradigm from recourse via nearest counterfactual explanations to recourse through minimal interventions, moving the focus from explanations to recommendations. Finally, we provide the reader with an extensive discussion on how to realistically achieve recourse beyond structural interventions.

研究动机与目标

• 在具有重大后果的决策中，激发对可操作追索超越反事实解释的需求。
• 批判“最近的反事实解直接转化为个人可行行动”的假设。
• 提出一种使用最小干预实现有利模型结果的因果重构。
• 通过合成数据和现实世界数据演示，最小干预在成本更低、可行性更高方面优于基于CFE的追索。

提出的方法

• 通过将现有反事实解释嵌入结构因果模型（SCM）来分析其局限性。
• 使用 do-operator 将行动形式化为干预，并通过 Abduction-Action-Prediction 计算结构化反事实。
• 定义基于 CFE 的行动，并在因果依赖下展示保证追索的必要/充分条件。
• 引入并求解 Minimal Interventions (MINT) 优化，目标是在确保 h(xSCF) 变化的同时最小化行动成本。

实验结果

研究问题

• RQ1 在因果依赖下，直接从反事实解释推导追索行动有哪些固有局限？
• RQ2 通过将行动框定为因果模型中的最小干预，是否能更可靠且更便宜地实现追索？
• RQ3 在合成数据和现实世界情境中，所提出的 Minimal Interventions 框架与基于 CFE 的追索相比如何？

主要发现

• CFE-based recourse can be suboptimal or infeasible in non-independent worlds due to causal dependencies.
• Recasting recourse as minimal interventions yields guaranteed recourse at lower cost when feasible actions are chosen over raw counterfactual shifts.
• In synthetic and German credit dataset experiments, minimal interventions require less effort for individuals to achieve favorable model outcomes compared to CFE-based actions.
• The Abduction-Action-Prediction framework enables computing structural counterfactuals for any feasible action set within additive noise SCMs.
• Minimal Interventions (MINT) provides a principled way to select actions that account for downstream effects of interventions on non-intervened variables.