Marrying Causal Representation Learning with Dynamical Systems for Science

TL;DR

This paper integrates causal representation learning with dynamical systems to develop identifiable, scalable models capable of handling real-world data and answering causal questions, demonstrated on climate data.

Contribution

It establishes a connection between causal learning and dynamical systems, enabling the use of identifiable methods and scalable solvers for practical, controllable models.

Findings

Successfully applied to wind simulator with known factors

Answered causal questions on climate data

Models are both identifiable and practical

Abstract

Causal representation learning promises to extend causal models to hidden causal variables from raw entangled measurements. However, most progress has focused on proving identifiability results in different settings, and we are not aware of any successful real-world application. At the same time, the field of dynamical systems benefited from deep learning and scaled to countless applications but does not allow parameter identification. In this paper, we draw a clear connection between the two and their key assumptions, allowing us to apply identifiable methods developed in causal representation learning to dynamical systems. At the same time, we can leverage scalable differentiable solvers developed for differential equations to build models that are both identifiable and practical. Overall, we learn explicitly controllable models that isolate the trajectory-specific parameters for further downstream tasks such as out-of-distribution classification or treatment effect estimation. We experiment with a wind simulator with partially known factors of variation. We also apply the resulting model to real-world climate data and successfully answer downstream causal questions in line with existing literature on climate change.