Amortized Inference for Causal Structure Learning

Lars Lorch, Scott Sussex, Jonas Rothfuss, Andreas Krause, Bernhard Schölkopf

Keywords: causality, amortized inference, causal discovery, structure learning, Bayesian causal discovery

TL;DR: Amortized causal discovery for learning realistic, domain-specific inductive bias

Abstract: Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and designing suitable scores or tests that capture prior knowledge is difficult. In this work, we propose to amortize causal structure learning. Rather than searching over structures, we train a variational inference model to directly predict the causal structure from observational or interventional data. This allows our inference model to acquire domain-specific inductive biases for causal discovery solely from data generated by a simulator, bypassing both the hand-engineering of suitable score functions and the search over graphs. The architecture of our inference model emulates permutation invariances that are crucial for statistical efficiency in structure learning, which facilitates generalization to significantly larger problem instances than seen during training. On synthetic data and semisynthetic gene expression data, our models exhibit robust generalization capabilities when subject to substantial distribution shifts and significantly outperform existing algorithms, especially in the challenging genomics domain. Our code and models are publicly available at: https://github.com/larslorch/avici

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:2205.12934/code)