Conditional Average Treatment Effect Distillation for Hypothetical State-Intervention Targeting Under Budget Constraints

📄 arXiv: 2610.25627v1 📥 PDF

作者: Vasundhara Acharya, Bülent Yener

分类: cs.LG

发布日期: 2026-10-19

备注: Under review at PLOS ONE

💡 一句话要点

提出条件平均治疗效应蒸馏以解决预算约束下的干预目标问题

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)

关键词: 因果蒸馏 个性化干预 预算约束 条件平均治疗效应 公共卫生政策 因果森林 贝叶斯因果森林 决策树

📋 核心要点

  1. 现有的因果效应模型难以在预算约束下有效实施，且粗略的子组政策可能导致个体化效应信息的丢失。
  2. 本文提出了一种因果蒸馏方法，通过因果森林和贝叶斯因果森林估计条件平均治疗效应，并将其转化为简化的预算干预规则。
  3. 实验结果显示，蒸馏学生的效用与教师相差极小，且在不同应用场景中，K均值和因果树政策表现出竞争力。

📝 摘要（中文）

个性化公共卫生干预必须在资源约束下捕捉异质性干预效益。灵活的因果效应模型难以操作，而粗略的子组政策可能丢失个体化效应信息。本文研究在没有历史决策政策的观察数据中，预算约束下的假设状态干预。通过因果森林和贝叶斯因果森林估计条件平均治疗效应（CATE），并与K均值子组政策和因果树政策进行比较。实验结果表明，蒸馏学生的效用与教师相差不超过0.011，且分配的Jaccard相似性在0.738到0.937之间，支持因果蒸馏在简化预算干预规则中的应用。

🔬 方法详解

问题定义：本文旨在解决在预算约束下如何有效实施个性化公共卫生干预的问题。现有方法在灵活性与可操作性之间存在矛盾，难以实现个体化干预效果的捕捉。

核心思路：论文提出通过因果蒸馏的方法，将复杂的因果效应模型转化为更简单的决策规则，以便在资源有限的情况下进行有效的干预。

技术框架：整体架构包括因果森林和贝叶斯因果森林作为教师模型，决策树和随机森林作为学生模型。通过对观察数据进行分析，评估不同政策的效果。

关键创新：最重要的创新在于引入因果蒸馏技术，使得复杂的因果模型能够被简化为预算友好的决策规则，这在现有文献中尚属首次。

关键设计：在模型中，预设了因果结构信息的协变量，并将容量限制在观察到的不良状态的70%。使用双重稳健估计器评估观察政策的效果，并通过引导法进行不确定性评估。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，蒸馏学生的效用与教师模型的绝对差异不超过0.011，分配的Jaccard相似性在0.738到0.937之间，表明蒸馏方法在保持决策质量方面表现优异。此外，K均值和因果树政策在不同应用中也展现出竞争力，进一步验证了该方法的有效性。

🎯 应用场景

该研究的潜在应用领域包括公共卫生政策制定、个性化医疗干预和社会科学研究等。通过提供一种在预算约束下有效实施个性化干预的方法，能够帮助决策者更好地分配资源，提高干预的有效性和可持续性。未来，该方法可能在其他领域的因果推断和决策制定中发挥重要作用。

📄 摘要（原文）

Personalized public-health targeting must capture heterogeneous intervention benefits while remaining interpretable under resource constraints. Flexible causal-effect models can be hard to operationalize, while coarse subgroup policies may lose individualized effect information. We study budget-constrained hypothetical state interventions in observational data without a logged historical decision policy. For obesity, elevated glucose, and lifetime smoking-history states, causal-structure-informed pretreatment covariates are prespecified, with capacity capped at 70% of those observed in the adverse state. We evaluate causal distillation where Causal Forest and Bayesian Causal Forest teachers estimate conditional average treatment effects (CATEs), which decision tree and random forest students approximate. We compare individualized policies with unsupervised K-means subgroup policies and supervised causal-tree policies with leaf counts matched to K-means cluster counts. Observational policies are assessed on held-out data using a doubly robust estimator, bootstrap uncertainty, and decision-focused teacher-student fidelity measures. Across PIMA obesity and glucose and NHANES smoking-history experiments, each distilled student was within 0.011 absolute utility of its teacher, with allocation Jaccard similarities of 0.738-0.937. K-means and causal-tree policies were also competitive, with the highest point-estimate policy varying by application. Prespecified paired comparisons were nonsignificant after Holm adjustment, while near-budget-boundary agreement was less stable than global fidelity for some teacher-student pairs. Findings support causal distillation for translating flexible effect models into simpler budgeted targeting rules, although observational estimates depend on causal-identification assumptions and require longitudinal or prospective validation.