Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models

Armin Kekić, Sergio Hernan Garrido Mejia, Bernhard Schölkopf
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29651-29669, 2025.

Abstract

Estimating causal effects of joint interventions on multiple variables is crucial in many domains, but obtaining data from such simultaneous interventions can be challenging. Our study explores how to learn joint interventional effects using only observational data and single-variable interventions. We present an identifiability result for this problem, showing that for a class of nonlinear additive outcome mechanisms, joint effects can be inferred without access to joint interventional data. We propose a practical estimator that decomposes the causal effect into confounded and unconfounded contributions for each intervention variable. Experiments on synthetic data demonstrate that our method achieves performance comparable to models trained directly on joint interventional data, outperforming a purely observational estimator.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-kekic25a, title = {Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models}, author = {Keki\'{c}, Armin and Garrido Mejia, Sergio Hernan and Sch\"{o}lkopf, Bernhard}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {29651--29669}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/kekic25a/kekic25a.pdf}, url = {https://proceedings.mlr.press/v267/kekic25a.html}, abstract = {Estimating causal effects of joint interventions on multiple variables is crucial in many domains, but obtaining data from such simultaneous interventions can be challenging. Our study explores how to learn joint interventional effects using only observational data and single-variable interventions. We present an identifiability result for this problem, showing that for a class of nonlinear additive outcome mechanisms, joint effects can be inferred without access to joint interventional data. We propose a practical estimator that decomposes the causal effect into confounded and unconfounded contributions for each intervention variable. Experiments on synthetic data demonstrate that our method achieves performance comparable to models trained directly on joint interventional data, outperforming a purely observational estimator.} }
Endnote
%0 Conference Paper %T Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models %A Armin Kekić %A Sergio Hernan Garrido Mejia %A Bernhard Schölkopf %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-kekic25a %I PMLR %P 29651--29669 %U https://proceedings.mlr.press/v267/kekic25a.html %V 267 %X Estimating causal effects of joint interventions on multiple variables is crucial in many domains, but obtaining data from such simultaneous interventions can be challenging. Our study explores how to learn joint interventional effects using only observational data and single-variable interventions. We present an identifiability result for this problem, showing that for a class of nonlinear additive outcome mechanisms, joint effects can be inferred without access to joint interventional data. We propose a practical estimator that decomposes the causal effect into confounded and unconfounded contributions for each intervention variable. Experiments on synthetic data demonstrate that our method achieves performance comparable to models trained directly on joint interventional data, outperforming a purely observational estimator.
APA
Kekić, A., Garrido Mejia, S.H. & Schölkopf, B.. (2025). Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:29651-29669 Available from https://proceedings.mlr.press/v267/kekic25a.html.

Related Material