On Data Manifolds Entailed by Structural Causal Models
Abstract
The geometric structure of data is an important inductive bias in machine learning. In this work, we characterize the data manifolds entailed by structural causal models. The strengths of the proposed framework are twofold: firstly, the geometric structure of the data manifolds is causally informed, and secondly, it enables causal reasoning about the data manifolds in an interventional and a counterfactual sense. We showcase the versatility of the proposed framework by applying it to the generation of causally-grounded counterfactual explanations for machine learning classifiers, measuring distances along the data manifold in a differential geometric-principled manner.
Cite
Text
Dominguez-Olmedo et al. "On Data Manifolds Entailed by Structural Causal Models." International Conference on Machine Learning, 2023.Markdown
[Dominguez-Olmedo et al. "On Data Manifolds Entailed by Structural Causal Models." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/dominguezolmedo2023icml-data/)BibTeX
@inproceedings{dominguezolmedo2023icml-data,
title = {{On Data Manifolds Entailed by Structural Causal Models}},
author = {Dominguez-Olmedo, Ricardo and Karimi, Amir-Hossein and Arvanitidis, Georgios and Schölkopf, Bernhard},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {8188-8201},
volume = {202},
url = {https://mlanthology.org/icml/2023/dominguezolmedo2023icml-data/}
}