A Characterization of Markov Equivalence Classes of Relational Causal Models under Path Semantics

Relational Causal Models (RCM) generalize Causal Bayesian Networks so as to extend causal discovery to relational domains. We provide a novel and elegant characterization of the Markov equivalence of RCMs under path semantics. We introduce a novel representation of unshielded triples that allows us to efficiently determine whether an RCM is Markov equivalent to another. Under path semantics, we provide a sound and complete algorithm for recovering the structure of an RCM from conditional independence queries. Our analysis also suggests ways to improve the orientation recall of algorithms for learning the structure of RCM under bridge burning semantics as well.