Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions

Fabio Massimo Zennaro, Máté Drávucz, Geanina Apachitei, W. Dhammika Widanage, Theodoros Damoulas
Proceedings of the Second Conference on Causal Learning and Reasoning, PMLR 213:88-121, 2023.

Abstract

An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution. Learning abstractions which guarantee consistency with respect to interventional distributions would allow one to jointly reason about evidence across multiple levels of granularity while respecting the underlying cause-effect relationships. In this paper, we introduce a first framework for causal abstraction learning between SCMs based on the formalization of abstraction recently proposed by Rischel (2020). Based on that, we propose a differentiable programming solution that jointly solves a number of combinatorial sub-problems, and we study its performance and benefits against independent and sequential approaches on synthetic settings and on a challenging real-world problem related to electric vehicle battery manufacturing.

Cite this Paper

BibTeX
@InProceedings{pmlr-v213-zennaro23a, title = {Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions}, author = {Zennaro, Fabio Massimo and Dr\'avucz, M\'at\'e and Apachitei, Geanina and Widanage, W. Dhammika and Damoulas, Theodoros}, booktitle = {Proceedings of the Second Conference on Causal Learning and Reasoning}, pages = {88--121}, year = {2023}, editor = {van der Schaar, Mihaela and Zhang, Cheng and Janzing, Dominik}, volume = {213}, series = {Proceedings of Machine Learning Research}, month = {11--14 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v213/zennaro23a/zennaro23a.pdf}, url = {https://proceedings.mlr.press/v213/zennaro23a.html}, abstract = {An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution. Learning abstractions which guarantee consistency with respect to interventional distributions would allow one to jointly reason about evidence across multiple levels of granularity while respecting the underlying cause-effect relationships. In this paper, we introduce a first framework for causal abstraction learning between SCMs based on the formalization of abstraction recently proposed by Rischel (2020). Based on that, we propose a differentiable programming solution that jointly solves a number of combinatorial sub-problems, and we study its performance and benefits against independent and sequential approaches on synthetic settings and on a challenging real-world problem related to electric vehicle battery manufacturing.} }
Endnote
%0 Conference Paper %T Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions %A Fabio Massimo Zennaro %A Máté Drávucz %A Geanina Apachitei %A W. Dhammika Widanage %A Theodoros Damoulas %B Proceedings of the Second Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2023 %E Mihaela van der Schaar %E Cheng Zhang %E Dominik Janzing %F pmlr-v213-zennaro23a %I PMLR %P 88--121 %U https://proceedings.mlr.press/v213/zennaro23a.html %V 213 %X An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution. Learning abstractions which guarantee consistency with respect to interventional distributions would allow one to jointly reason about evidence across multiple levels of granularity while respecting the underlying cause-effect relationships. In this paper, we introduce a first framework for causal abstraction learning between SCMs based on the formalization of abstraction recently proposed by Rischel (2020). Based on that, we propose a differentiable programming solution that jointly solves a number of combinatorial sub-problems, and we study its performance and benefits against independent and sequential approaches on synthetic settings and on a challenging real-world problem related to electric vehicle battery manufacturing.
APA
Zennaro, F.M., Drávucz, M., Apachitei, G., Widanage, W.D. & Damoulas, T.. (2023). Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions. Proceedings of the Second Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 213:88-121 Available from https://proceedings.mlr.press/v213/zennaro23a.html.

Related Material