重建不足够：基于学习多模态表征的双稳健反事实与干预中介分析
原标题：When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations
AI 摘要
该论文研究多模态健康记录的学习表征用于因果中介分析时的充分性问题。作者证明，仅依赖协变量的训练目标（重建、对比或物理约束）无法保证表征足以识别因果效应，且表征可损失极小重建精度却引入任意大偏差。他们提出结合模态特定VAE、交叉拟合双稳健估计器及表征不足诊断的工作流程，模拟中预测性诊断在100%重复中标记出丢弃罕见混杂因子的表征问题。
正文节选
When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations Abstract Learned representations of high-dimensional multimodal health records are increasingly used to adjust for confounding, yet they are usually trained to reconstruct the data rather than to preserve the information that causal identification requires. We study two families of estimands: counterfactual outcomes under alternative treatments, including