High Fidelity Image Counterfactuals with Probabilistic Causal Models

Fabio De Sousa Ribeiro, Tian Xia, Miguel Monteiro, Nick Pawlowski, Ben Glocker
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7390-7425, 2023.

Abstract

We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for high-dimensional structured variables, such as images, remains a challenging task. We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models. Our experiments demonstrate that our proposed mechanisms are capable of accurate abduction and estimation of direct, indirect and total effects as measured by axiomatic soundness of counterfactuals.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-de-sousa-ribeiro23a, title = {High Fidelity Image Counterfactuals with Probabilistic Causal Models}, author = {De Sousa Ribeiro, Fabio and Xia, Tian and Monteiro, Miguel and Pawlowski, Nick and Glocker, Ben}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {7390--7425}, 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/de-sousa-ribeiro23a/de-sousa-ribeiro23a.pdf}, url = {https://proceedings.mlr.press/v202/de-sousa-ribeiro23a.html}, abstract = {We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for high-dimensional structured variables, such as images, remains a challenging task. We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models. Our experiments demonstrate that our proposed mechanisms are capable of accurate abduction and estimation of direct, indirect and total effects as measured by axiomatic soundness of counterfactuals.} }
Endnote
%0 Conference Paper %T High Fidelity Image Counterfactuals with Probabilistic Causal Models %A Fabio De Sousa Ribeiro %A Tian Xia %A Miguel Monteiro %A Nick Pawlowski %A Ben Glocker %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-de-sousa-ribeiro23a %I PMLR %P 7390--7425 %U https://proceedings.mlr.press/v202/de-sousa-ribeiro23a.html %V 202 %X We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for high-dimensional structured variables, such as images, remains a challenging task. We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models. Our experiments demonstrate that our proposed mechanisms are capable of accurate abduction and estimation of direct, indirect and total effects as measured by axiomatic soundness of counterfactuals.
APA
De Sousa Ribeiro, F., Xia, T., Monteiro, M., Pawlowski, N. & Glocker, B.. (2023). High Fidelity Image Counterfactuals with Probabilistic Causal Models. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:7390-7425 Available from https://proceedings.mlr.press/v202/de-sousa-ribeiro23a.html.

Related Material