Paper ID: 2402.01929

Sample, estimate, aggregate: A recipe for causal discovery foundation models

Menghua Wu, Yujia Bao, Regina Barzilay, Tommi Jaakkola

Causal discovery, the task of inferring causal structure from data, promises to accelerate scientific research, inform policy making, and more. However, causal discovery algorithms over larger sets of variables tend to be brittle against misspecification or when data are limited. To mitigate these challenges, we train a supervised model that learns to predict a larger causal graph from the outputs of classical causal discovery algorithms run over subsets of variables, along with other statistical hints like inverse covariance. Our approach is enabled by the observation that typical errors in the outputs of classical methods remain comparable across datasets. Theoretically, we show that this model is well-specified, in the sense that it can recover a causal graph consistent with graphs over subsets. Empirically, we train the model to be robust to erroneous estimates using diverse synthetic data. Experiments on real and synthetic data demonstrate that this model maintains high accuracy in the face of misspecification or distribution shift, and can be adapted at low cost to different discovery algorithms or choice of statistics.

Submitted: Feb 2, 2024