Unsupervised Causal Abstractions Discovery
For researchers in causal inference, this provides a first step toward automated causal abstraction learning, though it is incremental as it builds on existing low-rank discovery techniques.
This work introduces a method to automatically discover high-level causal models from low-level data, leveraging low-rank causal discovery to learn causal abstractions without requiring expert hypotheses.
Causal abstractions formalize when a high-level structural causal model (SCM) captures the interventional behavior of a lower-level SCM. Existing applications of this notion largely follow a hypothesis-testing paradigm: an expert proposes a candidate high-level model and then evaluates if the low-level system implements it. We study the complementary problem of learning a high-level model directly from low-level measurements. Our contributions leverage hypotheses from low-rank causal discovery, and can be summarized as follows: (1) we show that observations generated by a low-rank graph induce latents that form a causal abstraction, (2) we provide identifiability results about these latents, and (3) we propose a practical objective to learn this high-level SCM.