Discovering Cyclic Causal Models with Latent Variables: A General SAT-Based Procedure

Abstract

We present a very general approach to learning the structure of causal models based on d-separation constraints, obtained from any given set of overlapping passive observational or experimental data sets. The procedure allows for both directed cycles (feedback loops) and the presence of latent variables. Our approach is based on a logical representation of causal pathways, which permits the integration of quite general background knowledge, and inference is performed using a Boolean satisfiability (SAT) solver. The procedure is complete in that it exhausts the available information on whether any given edge can be determined to be present or absent, and returns "unknown" otherwise. Many existing constraint-based causal discovery algorithms can be seen as special cases, tailored to circumstances in which one or more restricting assumptions apply. Simulations illustrate the effect of these assumptions on discovery and how the present algorithm scales.

Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013)

References in corpus (6)

• Directed Cyclic Graphical Representations of Feedback Models
• Identifying Independencies in Causal Graphs with Feedback
• On Deducing Conditional Independence from d-Separation in Causal Graphs with Feedback (Research Note)
• Bayesian Networks from the Point of View of Chain Graphs
• Modeling Discrete Interventional Data using Directed Cyclic Graphical Models
• Incorporating Causal Prior Knowledge as Path-Constraints in Bayesian Networks and Maximal Ancestral Graphs

Cited by in corpus (3)

• Constraint-based Causal Discovery from Multiple Interventions over Overlapping Variable Sets
• Foundations of Structural Causal Models with Cycles and Latent Variables
• Obtaining Causal Information by Merging Datasets with MAXENT