Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias

Raanan Yehezkel Rohekar, Shami Nisimov, Yaniv Gurwicz, Gal Novik

Keywords: Causal Discovery, Causal Structure Learning, Constraint-based Structure Learning, Causal Graph, Ancestral Graph Learning

TL;DR: We present a sound and complete algorithm for iteratively recovering causal graphs in the possible presence of latent confounders and selection bias.

Abstract: We present a sound and complete algorithm, called iterative causal discovery (ICD), for recovering causal graphs in the presence of latent confounders and selection bias. ICD relies on the causal Markov and faithfulness assumptions and recovers the equivalence class of the underlying causal graph. It starts with a complete graph, and consists of a single iterative stage that gradually refines this graph by identifying conditional independence (CI) between connected nodes. Independence and causal relations entailed after any iteration are correct, rendering ICD anytime. Essentially, we tie the size of the CI conditioning set to its distance on the graph from the tested nodes, and increase this value in the successive iteration. Thus, each iteration refines a graph that was recovered by previous iterations having smaller conditioning sets---a higher statistical power---which contributes to stability. We demonstrate empirically that ICD requires significantly fewer CI tests and learns more accurate causal graphs compared to FCI, FCI+, and RFCI algorithms.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://sites.google.com/view/icdalg