Causal Discovery under Off-Target Interventions

Davin Choo, Kirankumar Shiragur, Caroline Uhler
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:1621-1629, 2024.

Abstract

Causal graph discovery is a significant problem with applications across various disciplines. However, with observational data alone, the underlying causal graph can only be recovered up to its Markov equivalence class, and further assumptions or interventions are necessary to narrow down the true graph. This work addresses the causal discovery problem under the setting of stochastic interventions with the natural goal of minimizing the number of interventions performed. We propose the following stochastic intervention model which subsumes existing adaptive noiseless interventions in the literature while capturing scenarios such as fat-hand interventions and CRISPR gene knockouts: any intervention attempt results in an actual intervention on a random subset of vertices, drawn from a \emph{distribution dependent on attempted action}. Under this model, we study the two fundamental problems in causal discovery of verification and search and provide approximation algorithms with polylogarithmic competitive ratios and provide some preliminary experimental results.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-choo24a, title = {Causal Discovery under Off-Target Interventions}, author = {Choo, Davin and Shiragur, Kirankumar and Uhler, Caroline}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {1621--1629}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/choo24a/choo24a.pdf}, url = {https://proceedings.mlr.press/v238/choo24a.html}, abstract = {Causal graph discovery is a significant problem with applications across various disciplines. However, with observational data alone, the underlying causal graph can only be recovered up to its Markov equivalence class, and further assumptions or interventions are necessary to narrow down the true graph. This work addresses the causal discovery problem under the setting of stochastic interventions with the natural goal of minimizing the number of interventions performed. We propose the following stochastic intervention model which subsumes existing adaptive noiseless interventions in the literature while capturing scenarios such as fat-hand interventions and CRISPR gene knockouts: any intervention attempt results in an actual intervention on a random subset of vertices, drawn from a \emph{distribution dependent on attempted action}. Under this model, we study the two fundamental problems in causal discovery of verification and search and provide approximation algorithms with polylogarithmic competitive ratios and provide some preliminary experimental results.} }
Endnote
%0 Conference Paper %T Causal Discovery under Off-Target Interventions %A Davin Choo %A Kirankumar Shiragur %A Caroline Uhler %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-choo24a %I PMLR %P 1621--1629 %U https://proceedings.mlr.press/v238/choo24a.html %V 238 %X Causal graph discovery is a significant problem with applications across various disciplines. However, with observational data alone, the underlying causal graph can only be recovered up to its Markov equivalence class, and further assumptions or interventions are necessary to narrow down the true graph. This work addresses the causal discovery problem under the setting of stochastic interventions with the natural goal of minimizing the number of interventions performed. We propose the following stochastic intervention model which subsumes existing adaptive noiseless interventions in the literature while capturing scenarios such as fat-hand interventions and CRISPR gene knockouts: any intervention attempt results in an actual intervention on a random subset of vertices, drawn from a \emph{distribution dependent on attempted action}. Under this model, we study the two fundamental problems in causal discovery of verification and search and provide approximation algorithms with polylogarithmic competitive ratios and provide some preliminary experimental results.
APA
Choo, D., Shiragur, K. & Uhler, C.. (2024). Causal Discovery under Off-Target Interventions. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:1621-1629 Available from https://proceedings.mlr.press/v238/choo24a.html.

Related Material