Structural Causal Circuits: Probabilistic Circuits Climbing All Rungs of Pearl's Ladder of Causation

TMLR Paper4800 Authors

Abstract: The complexity and vastness of our world can require large models with numerous variables. Unfortunately, coming up with a model that is both accurate and able to provide predictions in a reasonable amount of time can prove difficult. One possibility to help overcome such problems is sum-product networks (SPNs), probabilistic models with the ability to tractably perform inference in linear time. In this paper, we extend SPNs' capabilities to the field of causality and introduce the family of structural causal circuits (SCCs), a type of SPNs capable of answering causal questions. Starting from conventional SPNs, we ``climb the ladder of causation'' and show how SCCs can represent not only observational but also interventional and counterfactual problems. We demonstrate successful application in different settings, ranging from simple binary variables to physics-based simulations.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Stefan_Feuerriegel1

Submission Number: 4800