Causal Discovery in Multivariate Time Series through Mutual Information Featurization

TL;DR

This paper introduces TD2C, a supervised learning framework that detects causal relationships in multivariate time series by recognizing persistent information flow asymmetries, outperforming traditional methods especially in complex, non-linear scenarios.

Contribution

The paper presents a novel pattern recognition approach to causal discovery in time series, moving beyond statistical tests to learn causal signatures directly from data.

Findings

TD2C achieves state-of-the-art performance on benchmarks.

It generalizes well to unseen dynamics without retraining.

Outperforms traditional causal discovery methods in high-dimensional, non-linear cases.

Abstract

Discovering causal relationships in complex multivariate time series is a fundamental scientific challenge. Traditional methods often falter, either by relying on restrictive linear assumptions or on conditional independence tests that become uninformative in the presence of intricate, non-linear dynamics. This paper proposes a new paradigm, shifting from statistical testing to pattern recognition. We hypothesize that a causal link creates a persistent and learnable asymmetry in the flow of information through a system's temporal graph, even when clear conditional independencies are obscured. We introduce Temporal Dependency to Causality (TD2C), a supervised learning framework that operationalizes this hypothesis. TD2C learns to recognize these complex causal signatures from a rich set of information-theoretic and statistical descriptors. Trained exclusively on a diverse collection of synthetic time series, TD2C demonstrates remarkable zero-shot generalization to unseen dynamics and established, realistic benchmarks. Our results show that TD2C achieves state-of-the-art performance, consistently outperforming established methods, particularly in high-dimensional and non-linear settings. By reframing the discovery problem, our work provides a robust and scalable new tool for uncovering causal structures in complex systems.