Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery
This work addresses the challenge of experimental design for researchers in fields requiring causal inference, offering an incremental improvement in low-data scenarios.
The paper tackles the problem of selecting the most informative intervention targets for causal discovery to minimize expensive experiments, proposing a gradient-based method that matches competitive baselines and surpasses them with limited data.
Inferring causal structure from data is a challenging task of fundamental importance in science. Observational data are often insufficient to identify a system's causal structure uniquely. While conducting interventions (i.e., experiments) can improve the identifiability, such samples are usually challenging and expensive to obtain. Hence, experimental design approaches for causal discovery aim to minimize the number of interventions by estimating the most informative intervention target. In this work, we propose a novel Gradient-based Intervention Targeting method, abbreviated GIT, that 'trusts' the gradient estimator of a gradient-based causal discovery framework to provide signals for the intervention acquisition function. We provide extensive experiments in simulated and real-world datasets and demonstrate that GIT performs on par with competitive baselines, surpassing them in the low-data regime.