Weakly Supervised Causal Representation Learning

Abstract

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 identifiable in a weakly supervised setting. This requires a dataset with paired samples before and after random, unknown interventions, but no further labels. Finally, we show that we can infer the representation and causal graph reliably in a simple synthetic domain using a variational autoencoder with a structural causal model as prior.

Cite

Text

Brehmer et al. "Weakly Supervised Causal Representation Learning." ICLR 2022 Workshops: OSC, 2022.

Markdown

[Brehmer et al. "Weakly Supervised Causal Representation Learning." ICLR 2022 Workshops: OSC, 2022.](https://mlanthology.org/iclrw/2022/brehmer2022iclrw-weakly/)

BibTeX

@inproceedings{brehmer2022iclrw-weakly,
  title     = {{Weakly Supervised Causal Representation Learning}},
  author    = {Brehmer, Johann and De Haan, Pim and Lippe, Phillip and Cohen, Taco},
  booktitle = {ICLR 2022 Workshops: OSC},
  year      = {2022},
  url       = {https://mlanthology.org/iclrw/2022/brehmer2022iclrw-weakly/}
}