From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders

Raanan Yehezkel Rohekar, Shami Nisimov, Yaniv Gurwicz, Gal Novik
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39939-39950, 2023.

Abstract

We present a constraint-based algorithm for learning causal structures from observational time-series data, in the presence of latent confounders. We assume a discrete-time, stationary structural vector autoregressive process, with both temporal and contemporaneous causal relations. One may ask if temporal and contemporaneous relations should be treated differently. The presented algorithm gradually refines a causal graph by learning long-term temporal relations before short-term ones, where contemporaneous relations are learned last. This ordering of causal relations to be learnt leads to a reduction in the required number of statistical tests. We validate this reduction empirically and demonstrate that it leads to higher accuracy for synthetic data and more plausible causal graphs for real-world data compared to state-of-the-art algorithms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-yehezkel-rohekar23a, title = {From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders}, author = {Yehezkel Rohekar, Raanan and Nisimov, Shami and Gurwicz, Yaniv and Novik, Gal}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {39939--39950}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/yehezkel-rohekar23a/yehezkel-rohekar23a.pdf}, url = {https://proceedings.mlr.press/v202/yehezkel-rohekar23a.html}, abstract = {We present a constraint-based algorithm for learning causal structures from observational time-series data, in the presence of latent confounders. We assume a discrete-time, stationary structural vector autoregressive process, with both temporal and contemporaneous causal relations. One may ask if temporal and contemporaneous relations should be treated differently. The presented algorithm gradually refines a causal graph by learning long-term temporal relations before short-term ones, where contemporaneous relations are learned last. This ordering of causal relations to be learnt leads to a reduction in the required number of statistical tests. We validate this reduction empirically and demonstrate that it leads to higher accuracy for synthetic data and more plausible causal graphs for real-world data compared to state-of-the-art algorithms.} }
Endnote
%0 Conference Paper %T From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders %A Raanan Yehezkel Rohekar %A Shami Nisimov %A Yaniv Gurwicz %A Gal Novik %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-yehezkel-rohekar23a %I PMLR %P 39939--39950 %U https://proceedings.mlr.press/v202/yehezkel-rohekar23a.html %V 202 %X We present a constraint-based algorithm for learning causal structures from observational time-series data, in the presence of latent confounders. We assume a discrete-time, stationary structural vector autoregressive process, with both temporal and contemporaneous causal relations. One may ask if temporal and contemporaneous relations should be treated differently. The presented algorithm gradually refines a causal graph by learning long-term temporal relations before short-term ones, where contemporaneous relations are learned last. This ordering of causal relations to be learnt leads to a reduction in the required number of statistical tests. We validate this reduction empirically and demonstrate that it leads to higher accuracy for synthetic data and more plausible causal graphs for real-world data compared to state-of-the-art algorithms.
APA
Yehezkel Rohekar, R., Nisimov, S., Gurwicz, Y. & Novik, G.. (2023). From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:39939-39950 Available from https://proceedings.mlr.press/v202/yehezkel-rohekar23a.html.

Related Material