CausalDynamics: A large-scale benchmark for structural discovery of dynamical causal models

TL;DR

CausalDynamics introduces a large-scale, extensible benchmark for evaluating causal discovery algorithms on complex dynamical systems, including stochastic, nonlinear, and climate models, to improve robustness and applicability.

Contribution

We present CausalDynamics, a comprehensive benchmark and data generation framework for structural discovery in dynamical causal models, addressing limitations of existing methods.

Findings

Evaluated state-of-the-art algorithms on diverse dynamical systems.

Demonstrated challenges in causal discovery with noisy and confounded data.

Provided a flexible, extensible platform for future research.

Abstract

Causal discovery for dynamical systems poses a major challenge in fields where active interventions are infeasible. Most methods used to investigate these systems and their associated benchmarks are tailored to deterministic, low-dimensional and weakly nonlinear time-series data. To address these limitations, we present CausalDynamics, a large-scale benchmark and extensible data generation framework to advance the structural discovery of dynamical causal models. Our benchmark consists of true causal graphs derived from thousands of both linearly and nonlinearly coupled ordinary and stochastic differential equations as well as two idealized climate models. We perform a comprehensive evaluation of state-of-the-art causal discovery algorithms for graph reconstruction on systems with noisy, confounded, and lagged dynamics. CausalDynamics consists of a plug-and-play, build-your-own coupling workflow that enables the construction of a hierarchy of physical systems. We anticipate that our framework will facilitate the development of robust causal discovery algorithms that are broadly applicable across domains while addressing their unique challenges. We provide a user-friendly implementation and documentation on https://kausable.github.io/CausalDynamics.