Imperial College London
Portrait Picture

DR BERNHARD KAINZ

Faculty of Engineering, Department of Computing

Reader in Medical Image Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8349b.kainz Website CV

 
 
//

Location

 

372Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Vlontzos:2023:10.1038/s42256-023-00611-x,
author = {Vlontzos, A and Kainz, B and Gilligan-Lee, CM},
doi = {10.1038/s42256-023-00611-x},
journal = {Nature Machine Intelligence},
pages = {159--168},
title = {Estimating categorical counterfactuals via deep twin networks},
url = {http://dx.doi.org/10.1038/s42256-023-00611-x},
volume = {5},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Counterfactual inference is a powerful tool, capable of solving challenging problems in high-profile sectors. To perform counterfactual inference, we require knowledge of the underlying causal mechanisms. However, causal mechanisms cannot be uniquely determined from observations and interventions alone. This raises the question of how to choose the causal mechanisms so that the resulting counterfactual inference is trustworthy in a given domain. This question has been addressed in causal models with binary variables, but for the case of categorical variables, it remains unanswered. We address this challenge by introducing for causal models with categorical variables the notion of counterfactual ordering, a principle positing desirable properties that causal mechanisms should possess and prove that it is equivalent to specific functional constraints on the causal mechanisms. To learn causal mechanisms satisfying these constraints, and perform counterfactual inference with them, we introduce deep twin networks. These are deep neural networks that, when trained, are capable of twin network counterfactual inference—an alternative to the abduction–action–prediction method. We empirically test our approach on diverse real-world and semisynthetic data from medicine, epidemiology and finance, reporting accurate estimation of counterfactual probabilities while demonstrating the issues that arise with counterfactual reasoning when counterfactual ordering is not enforced.
AU  - Vlontzos,A
AU  - Kainz,B
AU  - Gilligan-Lee,CM
DO  - 10.1038/s42256-023-00611-x
EP  - 168
PY  - 2023///
SN  - 2522-5839
SP  - 159
TI  - Estimating categorical counterfactuals via deep twin networks
T2  - Nature Machine Intelligence
UR  - http://dx.doi.org/10.1038/s42256-023-00611-x
UR  - http://hdl.handle.net/10044/1/102742
VL  - 5
ER  -
Download