Causal discovery with heterogeneous observational data
Fangting Zhou, Kejun He, Yang Ni
Abstract
We consider the problem of causal discovery (structure learning) from heterogeneous observational data. Most existing methods assume homogeneous sampling scheme and causal mechanism, which may lead to misleading conclusions when violated. 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 help explain sampling and causal heterogeneity. We investigate the 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 two real-world applications.
BibTeX
@InProceedings{pmlr-v180-zhou22a,
title = {Causal discovery with heterogeneous observational data},
author = {Zhou, Fangting and He, Kejun and Ni, Yang},
booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence},
pages = {2383--2393},
year = {2022},
editor = {Cussens, James and Zhang, Kun},
volume = {180},
series = {Proceedings of Machine Learning Research},
month = {01--05 Aug},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v180/zhou22a/zhou22a.pdf},
url = {https://proceedings.mlr.press/v180/zhou22a.html},
abstract = {We consider the problem of causal discovery (structure learning) from heterogeneous observational data. Most existing methods assume homogeneous sampling scheme and causal mechanism, which may lead to misleading conclusions when violated. 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 help explain sampling and causal heterogeneity. We investigate the 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 two real-world applications.}
}