Instrumental variable (IV) methods mitigate bias from unobserved confounding in observational causal inference but rely on the availability of a valid instrument, which can often be difficult or infeasible to identify in practice. In this paper, we propose a representation learning approach that constructs instrumental representations from observed covariates, which enable IV-based estimation even in the absence of an explicit instrument. Our model (ZNet) achieves this through an architecture that mirrors the structural causal model of IVs; it decomposes the ambient feature space into confounding and instrumental components, and is trained by enforcing empirical moment conditions corresponding to the defining properties of valid instruments (i.e., relevance, exclusion restriction, and instrumental unconfoundedness). Importantly, ZNet is compatible with a wide range of downstream two-stage IV estimators of causal effects. Our experiments demonstrate that ZNet can (i) recover ground-truth instruments when they already exist in the ambient feature space and (ii) construct latent instruments in the embedding space when no explicit IVs are available. This suggests that ZNet can be used as a ``plug-and-play'' module for causal inference in general observational settings, regardless of whether the (untestable) assumption of unconfoundedness is satisfied.

翻译：工具变量（IV）方法能够减轻观测性因果推断中未观测混杂因素带来的偏差，但其依赖于有效工具变量的可用性，而实践中有效工具变量的识别往往困难甚至不可行。本文提出一种表示学习方法，从观测协变量中构建工具变量表示，从而在缺乏显式工具变量的情况下仍能实现基于工具变量的估计。我们的模型（ZNet）通过一种镜像工具变量结构因果模型的架构实现这一目标：它将环境特征空间分解为混杂成分与工具成分，并通过强制满足有效工具变量定义属性（即相关性、排除限制与工具变量无混杂性）对应的经验矩条件进行训练。重要的是，ZNet与多种下游两阶段工具变量因果效应估计器兼容。实验表明，ZNet能够（i）在环境特征空间中已存在真实工具变量时将其恢复，并（ii）在无显式工具变量时在嵌入空间中构建潜在工具变量。这表明ZNet可作为通用观测场景下因果推断的“即插即用”模块，无论（不可检验的）无混杂性假设是否成立。