@inproceedings{19509,
  abstract     = {Machine Learning and AI have the potential to transform data-driven scientific discovery,
enabling accurate predictions for several scientific phenomena. As many scientific questions
are inherently causal, this paper looks at the causal inference task of treatment effect
estimation, where the outcome of interest is recorded in high-dimensional observations
in a Randomized Controlled Trial (RCT). Despite being the simplest possible causal setting
and a perfect fit for deep learning, we theoretically find that many common choices in the
literature may lead to biased estimates. To test the practical impact of these considerations,
we recorded ISTAnt, the first real-world benchmark for causal inference downstream tasks
on high-dimensional observations as an RCT studying how garden ants (Lasius neglectus)
respond to microparticles applied onto their colony members by hygienic grooming.
Comparing 6 480 models fine-tuned from state-of-the-art visual backbones, we find that
the sampling and modeling choices significantly affect the accuracy of the causal estimate,
and that classification accuracy is not a proxy thereof. We further validated the analysis,
repeating it on a synthetically generated visual data set controlling the causal model. Our
results suggest that future benchmarks should carefully consider real downstream scientific
questions, especially causal ones. Further, we highlight guidelines for representation
learning methods to help answer causal questions in the sciences.
Code: https://github.com/CausalLearningAI/ISTAnt
Data: https://doi.org/10.6084/m9.figshare.26484934.v2},
  author       = {Cadei, Riccardo and Lindorfer, Lukas and Cremer, Sylvia and Schmid, Cordelia and Locatello, Francesco},
  booktitle    = {38th Conference on Neural Information Processing Systems},
  issn         = {1049-5258},
  location     = {Vancouver, Canada},
  publisher    = {Neural Information Processing Systems Foundation},
  title        = {{Smoke and mirrors in causal downstream tasks}},
  doi          = {10.52202/079017-0820},
  volume       = {37},
  year         = {2024},
}