Nonlinear Causal Discovery for Grouped Data

Konstantin Göbler, Tobias Windisch, Mathias Drton
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:1453-1475, 2025.

Abstract

Inferring cause-effect relationships from observational data has gained significant attention in recent years, but most methods are limited to scalar random variables. In many important domains, including neuroscience, psychology, social science, and industrial manufacturing, the causal units of interest are groups of variables rather than individual scalar measurements. Motivated by these applications, we extend nonlinear additive noise models to handle random vectors, establishing a two-step approach for causal graph learning: First, infer the causal order among random vectors. Second, perform model selection to identify the best graph consistent with this order. We introduce effective and novel solutions for both steps in the vector case, demonstrating strong performance in simulations. Finally, we apply our method to real-world assembly line data with partial knowledge of causal ordering among variable groups.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-gobler25a, title = {Nonlinear Causal Discovery for Grouped Data}, author = {G\"{o}bler, Konstantin and Windisch, Tobias and Drton, Mathias}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {1453--1475}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/gobler25a/gobler25a.pdf}, url = {https://proceedings.mlr.press/v286/gobler25a.html}, abstract = {Inferring cause-effect relationships from observational data has gained significant attention in recent years, but most methods are limited to scalar random variables. In many important domains, including neuroscience, psychology, social science, and industrial manufacturing, the causal units of interest are groups of variables rather than individual scalar measurements. Motivated by these applications, we extend nonlinear additive noise models to handle random vectors, establishing a two-step approach for causal graph learning: First, infer the causal order among random vectors. Second, perform model selection to identify the best graph consistent with this order. We introduce effective and novel solutions for both steps in the vector case, demonstrating strong performance in simulations. Finally, we apply our method to real-world assembly line data with partial knowledge of causal ordering among variable groups.} }
Endnote
%0 Conference Paper %T Nonlinear Causal Discovery for Grouped Data %A Konstantin Göbler %A Tobias Windisch %A Mathias Drton %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-gobler25a %I PMLR %P 1453--1475 %U https://proceedings.mlr.press/v286/gobler25a.html %V 286 %X Inferring cause-effect relationships from observational data has gained significant attention in recent years, but most methods are limited to scalar random variables. In many important domains, including neuroscience, psychology, social science, and industrial manufacturing, the causal units of interest are groups of variables rather than individual scalar measurements. Motivated by these applications, we extend nonlinear additive noise models to handle random vectors, establishing a two-step approach for causal graph learning: First, infer the causal order among random vectors. Second, perform model selection to identify the best graph consistent with this order. We introduce effective and novel solutions for both steps in the vector case, demonstrating strong performance in simulations. Finally, we apply our method to real-world assembly line data with partial knowledge of causal ordering among variable groups.
APA
Göbler, K., Windisch, T. & Drton, M.. (2025). Nonlinear Causal Discovery for Grouped Data. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:1453-1475 Available from https://proceedings.mlr.press/v286/gobler25a.html.

Related Material