Inferring the time-varying coupling of dynamical systems with temporal convolutional autoencoders
This addresses the challenge of identifying time-varying causal interactions in physical and biological systems, though it appears incremental as it builds on existing machine learning architectures.
The paper tackled the problem of assessing causality in complex dynamical systems with non-linear and non-stationary interactions by introducing Temporal Autoencoders for Causal Inference (TACI), which accurately quantifies dynamic causal interactions in synthetic and real-world datasets.
Most approaches for assessing causality in complex dynamical systems fail when the interactions between variables are inherently non-linear and non-stationary. Here we introduce Temporal Autoencoders for Causal Inference (TACI), a methodology that combines a new surrogate data metric for assessing causal interactions with a novel two-headed machine learning architecture to identify and measure the direction and strength of time-varying causal interactions. Through tests on both synthetic and real-world datasets, we demonstrate TACI's ability to accurately quantify dynamic causal interactions across a variety of systems. Our findings display the method's effectiveness compared to existing approaches and also highlight our approach's potential to build a deeper understanding of the mechanisms that underlie time-varying interactions in physical and biological systems.