TY - JOUR
T1 - Causal Effect Identification in LiNGAM Models with Latent Confounders
AU - Tramontano, Daniele
AU - Kivva, Yaroslav
AU - Salehkaleybar, Saber
AU - Drton, Mathias
AU - Kiyavash, Negar
N1 - Publisher Copyright:
Copyright 2024 by the author(s)
PY - 2024
Y1 - 2024
N2 - We study the generic identifiability of causal effects in linear non-Gaussian acyclic models (LiNGAM) with latent variables. We consider the problem in two main settings: When the causal graph is known a priori, and when it is unknown. In both settings, we provide a complete graphical characterization of the identifiable direct or total causal effects among observed variables. Moreover, we propose efficient algorithms to certify the graphical conditions. Finally, we propose an adaptation of the reconstruction independent component analysis (RICA) algorithm that estimates the causal effects from the observational data given the causal graph. Experimental results show the effectiveness of the proposed method in estimating the causal effects.
AB - We study the generic identifiability of causal effects in linear non-Gaussian acyclic models (LiNGAM) with latent variables. We consider the problem in two main settings: When the causal graph is known a priori, and when it is unknown. In both settings, we provide a complete graphical characterization of the identifiable direct or total causal effects among observed variables. Moreover, we propose efficient algorithms to certify the graphical conditions. Finally, we propose an adaptation of the reconstruction independent component analysis (RICA) algorithm that estimates the causal effects from the observational data given the causal graph. Experimental results show the effectiveness of the proposed method in estimating the causal effects.
UR - http://www.scopus.com/inward/record.url?scp=85203823578&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85203823578
SN - 2640-3498
VL - 235
SP - 48468
EP - 48493
JO - Proceedings of Machine Learning Research
JF - Proceedings of Machine Learning Research
T2 - 41st International Conference on Machine Learning, ICML 2024
Y2 - 21 July 2024 through 27 July 2024
ER -