ICML 2022spotlight36 citations

On Measuring Causal Contributions via do-interventions

Yonghan Jung, Shiva Kasiviswanathan, Jin Tian, Dominik Janzing, Patrick Bloebaum, Elias Bareinboim

Abstract

Causal contributions measure the strengths of different causes to a target quantity. Understanding causal contributions is important in empirical sciences and data-driven disciplines since it allows to answer practical queries like “what are the contributions of each cause to the effect?” In this paper, we develop a principled method for quantifying causal contributions. First, we provide desiderata of properties axioms that causal contribution measures should satisfy and propose the do-Shapley values (inspired by do-interventions [Pearl, 2000]) as a unique method satisfying these properties. Next, we develop a criterion under which the do-Shapley values can be efficiently inferred from non-experimental data. Finally, we provide do-Shapley estimators exhibiting consistency, computational feasibility, and statistical robustness. Simulation results corroborate with the theory.

BibTeX
@InProceedings{pmlr-v162-jung22a,
  title = 	 {On Measuring Causal Contributions via do-interventions},
  author =       {Jung, Yonghan and Kasiviswanathan, Shiva and Tian, Jin and Janzing, Dominik and Bloebaum, Patrick and Bareinboim, Elias},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {10476--10501},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/jung22a/jung22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/jung22a.html},
  abstract = 	 {Causal contributions measure the strengths of different causes to a target quantity. Understanding causal contributions is important in empirical sciences and data-driven disciplines since it allows to answer practical queries like “what are the contributions of each cause to the effect?” In this paper, we develop a principled method for quantifying causal contributions. First, we provide desiderata of properties axioms that causal contribution measures should satisfy and propose the do-Shapley values (inspired by do-interventions [Pearl, 2000]) as a unique method satisfying these properties. Next, we develop a criterion under which the do-Shapley values can be efficiently inferred from non-experimental data. Finally, we provide do-Shapley estimators exhibiting consistency, computational feasibility, and statistical robustness. Simulation results corroborate with the theory.}
}
On Measuring Causal Contributions via do-interventions · ICML 2022