Temporal latent variable structural causal model for causal discovery under external interferences

• Published in: Neurocomputing (Amsterdam) Vol. 640; p. 130281
• Main Authors: Cai, Ruichu, Huang, Xiaokai, Chen, Wei, Li, Zijian, Hao, Zhifeng
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2025
• Subjects: Causal discovery; External interference; Latent variables; Temporal data; Variational inference; Latent variables; Temporal data; Variational inference; External interference; Causal discovery
• ISSN: 0925-2312
• DOI: 10.1016/j.neucom.2025.130281

Inferring causal relationships from observed data is an important task, yet it becomes challenging when the data is subject to various external interferences. Most of these interferences are the additional effects of external factors on observed variables. Since these external factors are often unknown, we introduce latent variables to represent these unobserved factors that affect the observed data. Specifically, to capture the causal strength and adjacency information, we propose a new temporal latent variable structural causal model, incorporating causal strength and adjacency coefficients that represent the causal relationships between variables. Considering that expert knowledge can provide information about unknown interferences in certain scenarios, we develop a method that facilitates the incorporation of prior knowledge into parameters learning based on Variational Inference, to guide the model estimation. Experimental results demonstrate the stability and accuracy of our proposed method. •We propose a Temporal Latent Variable Structural Causal Model for causal discovery with external interferences.•We use a Hadamard product of adjacency and weight matrices to constrain model complexity.•We estimate the model using variational inference, integrating expert knowledge as a prior.