Causal discovery with heterogeneous observational data
Causal discovery with heterogeneous observational data
复制标题
DOI：
--
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Fangting Zhou;Kejun He;Yang Ni
中科院分区：
文献类型：
--
作者：
Fangting Zhou;Kejun He;Yang Ni
我们考虑的问题，因果发现（结构学习）从异质观测数据。大多数现有的方法假设一个均匀的抽样方案，这导致误导性的结论时，违反了在许多应用中。为此，我们提出了一种新的方法，利用数据的异质性来推断因果关系不足的系统可能循环因果结构。其核心思想是将直接因果效应建模为外生协变量的函数，从而正确解释数据的异质性。我们研究所提出的模型的结构可识别性。结构学习以完全贝叶斯的方式进行，这提供了自然的不确定性量化。我们通过大量的模拟和现实世界的应用程序证明了它的实用性。
We consider the problem of causal discovery (structure learning) from heterogeneous observational data. Most existing methods assume a homogeneous sampling scheme, which leads to misleading conclusions when violated in many applications. To this end, we propose a novel approach that exploits data heterogeneity to infer possibly cyclic causal structures from causally insufficient systems. The core idea is to model the direct causal effects as functions of exogenous covariates that properly explain data heterogeneity. We investigate structure identifiability properties of the proposed model. Structure learning is carried out in a fully Bayesian fashion, which provides natural uncertainty quantification. We demonstrate its utility through extensive simulations and a real-world application.