Predicting potential and counterfactual outcomes from observational data is central to individualized decision-making, particularly in clinical settings where treatment choices must be tailored to each patient rather than guided solely by population averages. We propose PO-Flow, a continuous normalizing flow (CNF) framework for causal inference that jointly models potential outcome distributions and factual-conditioned counterfactual outcomes. Trained via flow matching, PO-Flow provides a unified approach to individualized potential outcome prediction, conditional average treatment effect estimation, and counterfactual prediction. By encoding an observed factual outcome into a shared latent representation and decoding it under an alternative treatment, PO-Flow relates factual and counterfactual realizations at the individual level, rather than generating counterfactuals independently from marginal conditional distributions. In addition, PO-Flow supports likelihood-based evaluation of potential outcomes, enabling uncertainty-aware assessment of predictions. A supporting recovery guarantee is established under certain assumptions, and empirical results on benchmark datasets demonstrate strong performance across a range of causal inference tasks within the potential outcomes framework.

翻译：从观测数据中预测潜在结果与反事实结果是个体化决策的核心，尤其在临床环境中，治疗方案的选择必须针对每位患者量身定制，而非仅依据群体平均值进行指导。我们提出了PO-Flow，一种用于因果推断的连续归一化流（CNF）框架，该框架联合建模潜在结果分布与事实条件下的反事实结果。通过流匹配训练，PO-Flow为个体化潜在结果预测、条件平均处理效应估计及反事实预测提供了统一方法。PO-Flow将观测到的事实结果编码为共享的潜在表示，并在替代处理下进行解码，从而在个体层面关联事实与反事实的实现，而非从边际条件分布中独立生成反事实。此外，PO-Flow支持基于似然的潜在结果评估，实现了对预测的不确定性感知评估。我们在特定假设下建立了相应的恢复性保证，并在基准数据集上的实证结果表明，该框架在潜在结果范式下的多种因果推断任务中均表现出色。