Learning stable and predictive structures in kinetic systems: Benefits of a causal approach

TL;DR

This paper introduces CausalKinetiX, a causal approach for learning stable, predictive structures in kinetic systems from noisy, heterogeneous data, improving out-of-sample generalization.

Contribution

The paper presents a novel, computationally efficient framework that leverages causal principles to identify invariant kinetic models from discrete, noisy observations.

Findings

CausalKinetiX outperforms existing methods in predictive accuracy.

The approach yields concise, interpretable models across different experiments.

Significant improvements in out-of-sample prediction accuracy were observed.

Abstract

Learning kinetic systems from data is one of the core challenges in many fields. Identifying stable models is essential for the generalization capabilities of data-driven inference. We introduce a computationally efficient framework, called CausalKinetiX, that identifies structure from discrete time, noisy observations, generated from heterogeneous experiments. The algorithm assumes the existence of an underlying, invariant kinetic model, a key criterion for reproducible research. Results on both simulated and real-world examples suggest that learning the structure of kinetic systems benefits from a causal perspective. The identified variables and models allow for a concise description of the dynamics across multiple experimental settings and can be used for prediction in unseen experiments. We observe significant improvements compared to well established approaches focusing solely on predictive performance, especially for out-of-sample generalization.