Learning high-level causal representations together with a causal model from unstructured low-level data such as pixels is impossible from observational data alone. We prove under mild assumptions that this representation is however identifiable in a weakly supervised setting. This involves a dataset with paired samples before and after random, unknown interventions, but no further labels. We then introduce implicit latent causal models, variational autoencoders that represent causal variables and causal structure without having to optimize an explicit discrete graph structure. On simple image data, including a novel dataset of simulated robotic manipulation, we demonstrate that such models can reliably identify the causal structure and disentangle causal variables.
@article{arxiv.2203.16437,
title = {Weakly supervised causal representation learning},
author = {Johann Brehmer and Pim de Haan and Phillip Lippe and Taco Cohen},
journal= {arXiv preprint arXiv:2203.16437},
year = {2022}
}
Comments
Published at NeurIPS 2022. v3: Experiments with higher-dimensional data and larger graphs, improved writing, and added references; matches camera-ready version