Heterogeneous Treatment Effect (HTE) identification is crucial to explain the impact of an intervention and optimize our policies accordingly. Existing approaches trade expressivity for interpretability, but, if some active heterogeneity drivers are unmeasured, methods at both ends of this spectrum allow for spurious HTE characterization with no causal reading. In this work, we focus on controlled experiments and argue that an oracle HTE causal characterization via the latent interactors is now within reach, thanks to (i) more extensive pre-treatment measurements, i.e., multi-modal and multi-view, and (ii) scalable representations with minimal human supervision. We then re-frame HTE identification as a Markov-blanket discovery problem on a sufficient and aligned pre-treatment representation, and introduce Neural EXposure Interaction Search (NEXIS), an iterative procedure with provable and empirically validated consistent selection. We deploy NEXIS on two anti-poverty programs in Africa, augmenting each with satellite imagery capturing previously unmeasured environmental effect modifiers, leading to novel, interpretable and prescriptive guidelines to optimize the programs' next iterations.

翻译：异质性处理效应识别对于解释干预措施的影响并优化相应策略至关重要。现有方法在可表达性与可解释性之间存在权衡，但若某些活跃的异质性驱动因素未被测量，则处于该光谱两端的各类方法均可能产生无法进行因果解读的虚假异质性表征。本研究聚焦于受控实验，论证了通过潜在交互因子实现预言机级别因果异质性表征如今已触手可及，这得益于：(i) 更广泛的预处理测量（即多模态与多视角数据），(ii) 需要最少人类监督的可扩展表征。我们将异质性处理效应识别重新定义为充分对齐的预处理表征上的马尔可夫毯发现问题，并提出神经暴露交互搜索（NEXIS）——一种具有可证明且经经验验证一致选择性的迭代算法。我们在非洲两项反贫困项目中部署NEXIS，通过卫星图像补充先前未测量的环境效应修饰因子，从而生成新颖、可解释且具规范性的指导方针，以优化这些项目的后续迭代。