Estimate Collapsibility of Causal Effects in Completed Partial DAGs via Strong d-Convex Hulls
2026-06-08 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new method to estimate cause-and-effect relationships in complex graphs that keeps results reliable even when some variables are ignored. They defined a concept called 'estimate collapsibility' and identified minimal groups of variables important for accurate estimation. They created an efficient algorithm to find these groups in two types of graphs (DAGs and CPDAGs) and combined this with an existing causal inference method called IDA. Their experiments show that this approach improves causal estimation in these graph models.
causal effectsCPDAGDAGestimate collapsibilitystrong d-convex hullgraph reductionIDA frameworkcausal inferencealgorithms
Authors
Yuxin Deng, Yi Sun, Zhiming Li, Huaxiong Liu
Abstract
This paper proposes a collapsible method for estimating causal effects that maintains the estimator's consistency before and after marginalization over some variables in completed partially directed acyclic graphs (CPDAGs). We first introduce the estimate collapsibility for CPDAGs and characterize the minimal collapsible sets as strong d-convex hulls. An efficient algorithm is devised to obtain such sets in DAGs and is generalized to CPDAGs. Then, we combine the graph reduction procedure with the IDA framework. Finally, experiments and empirical analysis show the effectiveness of the collapsibility for causal estimations in CPDAGs. Code is available at https://github.com/Jamyang-D/strongly-convex.