Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis

Rémi Khellaf, Aurélien Bellet, Julie Josse
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:3448-3456, 2025.

Abstract

We study Federated Causal Inference, an approach to estimate treatment effects from decentralized data across centers. We compare three classes of Average Treatment Effect (ATE) estimators derived from the Plug-in G-Formula, ranging from simple meta-analysis to one-shot and multi-shot federated learning, the latter leveraging the full data to learn the outcome model (albeit requiring more communication). Focusing on Randomized Controlled Trials (RCTs), we derive the asymptotic variance of these estimators for linear models. Our results provide practical guidance on selecting the appropriate estimator for various scenarios, including heterogeneity in sample sizes, covariate distributions, treatment assignment schemes, and center effects. We validate these findings with a simulation study.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-khellaf25a, title = {Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis}, author = {Khellaf, R{\'e}mi and Bellet, Aur{\'e}lien and Josse, Julie}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {3448--3456}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/khellaf25a/khellaf25a.pdf}, url = {https://proceedings.mlr.press/v258/khellaf25a.html}, abstract = {We study Federated Causal Inference, an approach to estimate treatment effects from decentralized data across centers. We compare three classes of Average Treatment Effect (ATE) estimators derived from the Plug-in G-Formula, ranging from simple meta-analysis to one-shot and multi-shot federated learning, the latter leveraging the full data to learn the outcome model (albeit requiring more communication). Focusing on Randomized Controlled Trials (RCTs), we derive the asymptotic variance of these estimators for linear models. Our results provide practical guidance on selecting the appropriate estimator for various scenarios, including heterogeneity in sample sizes, covariate distributions, treatment assignment schemes, and center effects. We validate these findings with a simulation study.} }
Endnote
%0 Conference Paper %T Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis %A Rémi Khellaf %A Aurélien Bellet %A Julie Josse %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-khellaf25a %I PMLR %P 3448--3456 %U https://proceedings.mlr.press/v258/khellaf25a.html %V 258 %X We study Federated Causal Inference, an approach to estimate treatment effects from decentralized data across centers. We compare three classes of Average Treatment Effect (ATE) estimators derived from the Plug-in G-Formula, ranging from simple meta-analysis to one-shot and multi-shot federated learning, the latter leveraging the full data to learn the outcome model (albeit requiring more communication). Focusing on Randomized Controlled Trials (RCTs), we derive the asymptotic variance of these estimators for linear models. Our results provide practical guidance on selecting the appropriate estimator for various scenarios, including heterogeneity in sample sizes, covariate distributions, treatment assignment schemes, and center effects. We validate these findings with a simulation study.
APA
Khellaf, R., Bellet, A. & Josse, J.. (2025). Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:3448-3456 Available from https://proceedings.mlr.press/v258/khellaf25a.html.

Related Material