Practical Algorithms for Orientations of Partially Directed Graphical Models
This work addresses a key subroutine in causal discovery algorithms, such as the PC algorithm, by improving efficiency for researchers and practitioners in fields like observational studies, though it is incremental in nature.
The paper tackles the maximal orientation task for partially directed acyclic graphs (PDAGs) in causal discovery, aiming to orient undirected edges maximally while preserving Markov equivalence, and proposes two novel algorithms that achieve faster computation with an emphasis on simplicity and practical effectiveness.
In observational studies, the true causal model is typically unknown and needs to be estimated from available observational and limited experimental data. In such cases, the learned causal model is commonly represented as a partially directed acyclic graph (PDAG), which contains both directed and undirected edges indicating uncertainty of causal relations between random variables. The main focus of this paper is on the maximal orientation task, which, for a given PDAG, aims to orient the undirected edges maximally such that the resulting graph represents the same Markov equivalent DAGs as the input PDAG. This task is a subroutine used frequently in causal discovery, e. g., as the final step of the celebrated PC algorithm. Utilizing connections to the problem of finding a consistent DAG extension of a PDAG, we derive faster algorithms for computing the maximal orientation by proposing two novel approaches for extending PDAGs, both constructed with an emphasis on simplicity and practical effectiveness.