In causality, estimating the effect of a treatment without confounding inference remains a major issue because requires to assess the outcome in both case with and without treatment. Not being able to observe simultaneously both of them, the estimation of potential outcome remains a challenging task. We propose an innovative approach where the problem is reformulated as a missing data model. The aim is to estimate the hidden distribution of \emph{causal populations}, defined as a function of treatment and outcome. A Causal Auto-Encoder (CAE), enhanced by a prior dependent on treatment and outcome information, assimilates the latent space to the probability distribution of the target populations. The features are reconstructed after being reduced to a latent space and constrained by a mask introduced in the intermediate layer of the network, containing treatment and outcome information.

翻译：在因果关系方面,在不混淆推断的情况下估计治疗的效果仍然是一个重大问题,因为需要评估两种情况的结果,无论治疗与否。如果无法同时观察这两个情况,估计潜在结果仍然是一项艰巨的任务。我们建议采取创新办法,将问题重新拟订为缺失的数据模型,目的是估计被界定为治疗和结果的函数的memph{causal人口}的隐性分布。一个Causal Auto-Encoder(CAE),在先前依赖治疗和结果信息的情况下,将潜在空间与目标人口的概率分布相提并论。这些特征在缩小为潜在空间并受到网络中间层引入的含有治疗和结果信息的面具的限制之后,再加以重建。