UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems

TL;DR

UnCLe is a deep learning framework designed to uncover evolving causal relationships in dynamic systems from time series data, outperforming existing methods in accuracy and capturing temporal causality.

Contribution

It introduces a novel pair of neural networks and auto-regressive dependency matrices to effectively discover and model time-varying causal influences.

Findings

Outperforms state-of-the-art static causal discovery methods

Accurately captures dynamic causality in synthetic systems

Effectively models real-world systems like human motion

Abstract

Uncovering cause-effect relationships from observational time series is fundamental to understanding complex systems. While many methods infer static causal graphs, real-world systems often exhibit dynamic causality-where relationships evolve over time. Accurately capturing these temporal dynamics requires time-resolved causal graphs. We propose UnCLe, a novel deep learning method for scalable dynamic causal discovery. UnCLe employs a pair of Uncoupler and Recoupler networks to disentangle input time series into semantic representations and learns inter-variable dependencies via auto-regressive Dependency Matrices. It estimates dynamic causal influences by analyzing datapoint-wise prediction errors induced by temporal perturbations. Extensive experiments demonstrate that UnCLe not only outperforms state-of-the-art baselines on static causal discovery benchmarks but, more importantly, exhibits a unique capability to accurately capture and represent evolving temporal causality in both synthetic and real-world dynamic systems (e.g., human motion). UnCLe offers a promising approach for revealing the underlying, time-varying mechanisms of complex phenomena.