Shapley-PC: Constraint-based Causal Structure Learning with a Shapley Inspired Framework

Fabrizio Russo, Francesca Toni
Proceedings of the Fourth Conference on Causal Learning and Reasoning, PMLR 275:292-339, 2025.

Abstract

Causal Structure Learning (CSL), also referred to as causal discovery, amounts to extracting causal relations among variables in data. CSL enables the estimation of causal effects from observational data alone, avoiding the need to perform real life experiments. Constraint-based CSL leverages conditional independence tests to perform causal discovery. We propose Shapley-PC, a novel method to improve constraint-based CSL algorithms by using Shapley values over the possible conditioning sets, to decide which variables are responsible for the observed conditional (in)dependences. We prove soundness, completeness and asymptotic consistency of Shapley-PC and run a simulation study showing that our proposed algorithm is superior to existing versions of PC.

Cite this Paper

BibTeX
@InProceedings{pmlr-v275-russo25a, title = {Shapley-PC: Constraint-based Causal Structure Learning with a Shapley Inspired Framework}, author = {Russo, Fabrizio and Toni, Francesca}, booktitle = {Proceedings of the Fourth Conference on Causal Learning and Reasoning}, pages = {292--339}, year = {2025}, editor = {Huang, Biwei and Drton, Mathias}, volume = {275}, series = {Proceedings of Machine Learning Research}, month = {07--09 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v275/main/assets/russo25a/russo25a.pdf}, url = {https://proceedings.mlr.press/v275/russo25a.html}, abstract = {Causal Structure Learning (CSL), also referred to as causal discovery, amounts to extracting causal relations among variables in data. CSL enables the estimation of causal effects from observational data alone, avoiding the need to perform real life experiments. Constraint-based CSL leverages conditional independence tests to perform causal discovery. We propose Shapley-PC, a novel method to improve constraint-based CSL algorithms by using Shapley values over the possible conditioning sets, to decide which variables are responsible for the observed conditional (in)dependences. We prove soundness, completeness and asymptotic consistency of Shapley-PC and run a simulation study showing that our proposed algorithm is superior to existing versions of PC.} }
Endnote
%0 Conference Paper %T Shapley-PC: Constraint-based Causal Structure Learning with a Shapley Inspired Framework %A Fabrizio Russo %A Francesca Toni %B Proceedings of the Fourth Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Biwei Huang %E Mathias Drton %F pmlr-v275-russo25a %I PMLR %P 292--339 %U https://proceedings.mlr.press/v275/russo25a.html %V 275 %X Causal Structure Learning (CSL), also referred to as causal discovery, amounts to extracting causal relations among variables in data. CSL enables the estimation of causal effects from observational data alone, avoiding the need to perform real life experiments. Constraint-based CSL leverages conditional independence tests to perform causal discovery. We propose Shapley-PC, a novel method to improve constraint-based CSL algorithms by using Shapley values over the possible conditioning sets, to decide which variables are responsible for the observed conditional (in)dependences. We prove soundness, completeness and asymptotic consistency of Shapley-PC and run a simulation study showing that our proposed algorithm is superior to existing versions of PC.
APA
Russo, F. & Toni, F.. (2025). Shapley-PC: Constraint-based Causal Structure Learning with a Shapley Inspired Framework. Proceedings of the Fourth Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 275:292-339 Available from https://proceedings.mlr.press/v275/russo25a.html.

Related Material