Lifted Causal Inference in Relational Domains

Malte Luttermann, Mattis Hartwig, Tanya Braun, Ralf Möller, Marcel Gehrke
Proceedings of the Third Conference on Causal Learning and Reasoning, PMLR 236:827-842, 2024.

Abstract

Lifted inference exploits symmetries in probabilistic graphical models by using a representative for indistinguishable objects, thereby speeding up query answering while maintaining exact answers. Even though lifting is a well-established technique for the task of probabilistic inference in relational domains, it has not yet been applied to the task of causal inference. In this paper, we show how lifting can be applied to efficiently compute causal effects in relational domains. More specifically, we introduce parametric causal factor graphs as an extension of parametric factor graphs incorporating causal knowledge and give a formal semantics of interventions therein. We further present the lifted causal inference algorithm to compute causal effects on a lifted level, thereby drastically speeding up causal inference compared to propositional inference, e.g., in causal Bayesian networks. In our empirical evaluation, we demonstrate the effectiveness of our approach.

Cite this Paper


BibTeX
@InProceedings{pmlr-v236-luttermann24a, title = {Lifted Causal Inference in Relational Domains}, author = {Luttermann, Malte and Hartwig, Mattis and Braun, Tanya and M\"oller, Ralf and Gehrke, Marcel}, booktitle = {Proceedings of the Third Conference on Causal Learning and Reasoning}, pages = {827--842}, year = {2024}, editor = {Locatello, Francesco and Didelez, Vanessa}, volume = {236}, series = {Proceedings of Machine Learning Research}, month = {01--03 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v236/luttermann24a/luttermann24a.pdf}, url = {https://proceedings.mlr.press/v236/luttermann24a.html}, abstract = {Lifted inference exploits symmetries in probabilistic graphical models by using a representative for indistinguishable objects, thereby speeding up query answering while maintaining exact answers. Even though lifting is a well-established technique for the task of probabilistic inference in relational domains, it has not yet been applied to the task of causal inference. In this paper, we show how lifting can be applied to efficiently compute causal effects in relational domains. More specifically, we introduce parametric causal factor graphs as an extension of parametric factor graphs incorporating causal knowledge and give a formal semantics of interventions therein. We further present the lifted causal inference algorithm to compute causal effects on a lifted level, thereby drastically speeding up causal inference compared to propositional inference, e.g., in causal Bayesian networks. In our empirical evaluation, we demonstrate the effectiveness of our approach.} }
Endnote
%0 Conference Paper %T Lifted Causal Inference in Relational Domains %A Malte Luttermann %A Mattis Hartwig %A Tanya Braun %A Ralf Möller %A Marcel Gehrke %B Proceedings of the Third Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2024 %E Francesco Locatello %E Vanessa Didelez %F pmlr-v236-luttermann24a %I PMLR %P 827--842 %U https://proceedings.mlr.press/v236/luttermann24a.html %V 236 %X Lifted inference exploits symmetries in probabilistic graphical models by using a representative for indistinguishable objects, thereby speeding up query answering while maintaining exact answers. Even though lifting is a well-established technique for the task of probabilistic inference in relational domains, it has not yet been applied to the task of causal inference. In this paper, we show how lifting can be applied to efficiently compute causal effects in relational domains. More specifically, we introduce parametric causal factor graphs as an extension of parametric factor graphs incorporating causal knowledge and give a formal semantics of interventions therein. We further present the lifted causal inference algorithm to compute causal effects on a lifted level, thereby drastically speeding up causal inference compared to propositional inference, e.g., in causal Bayesian networks. In our empirical evaluation, we demonstrate the effectiveness of our approach.
APA
Luttermann, M., Hartwig, M., Braun, T., Möller, R. & Gehrke, M.. (2024). Lifted Causal Inference in Relational Domains. Proceedings of the Third Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 236:827-842 Available from https://proceedings.mlr.press/v236/luttermann24a.html.

Related Material