Causal Discovery from Conditionally Stationary Time Series

TL;DR

This paper introduces SDCI, a novel causal discovery method for nonstationary time series that models stationarity conditioned on latent states, enabling the recovery of causal structures in complex data.

Contribution

The paper presents a new approach called State-Dependent Causal Inference (SDCI) that handles nonstationary time series with provable identifiability of causal structures.

Findings

SDCI outperforms baseline methods on nonlinear particle interaction data.

SDCI achieves better causal structure recovery in gene regulatory network data.

SDCI improves forecasting accuracy over non-causal RNNs in NBA player movement prediction.

Abstract

Causal discovery, i.e., inferring underlying causal relationships from observational data, is highly challenging for AI systems. In a time series modeling context, traditional causal discovery methods mainly consider constrained scenarios with fully observed variables and/or data from stationary time-series. We develop a causal discovery approach to handle a wide class of nonstationary time series that are conditionally stationary, where the nonstationary behaviour is modeled as stationarity conditioned on a set of latent state variables. Named State-Dependent Causal Inference (SDCI), our approach is able to recover the underlying causal dependencies, with provable identifiablity for the state-dependent causal structures. Empirical experiments on nonlinear particle interaction data and gene regulatory networks demonstrate SDCI's superior performance over baseline causal discovery methods. Improved results over non-causal RNNs on modeling NBA player movements demonstrate the potential of our method and motivate the use of causality-driven methods for forecasting.