Search papers, labs, and topics across Lattice.
This paper addresses the challenge of learning causal representations from time-series data by jointly modeling instantaneous and lagged causal relations under nonstationarity. The authors establish theoretical conditions for identifiability of latent states and their causal structures using an auxiliary variable and propose iCReN, a contrastive learning framework to achieve this. Experiments show iCReN accurately recovers latent states and both types of causal relations, demonstrating its utility for downstream forecasting.
Unlocking causal discovery in time-series by disentangling instantaneous and lagged influences, even with nonstationary dynamics.
Causal representation learning for time-series data aims to identify latent states and their causal relations from observations. In this setting, an important challenge is to model both lagged causal relations across observation intervals and faster causal effects that appear as instantaneous relations within an interval, while accounting for nonstationarity in time-series data. However, methods that jointly handle these causal relations and nonstationarity remain limited. To address this gap, we establish sufficient conditions for identifying latent states up to component permutation and component-wise invertible transformations, and their instantaneous and lagged causal structures up to the same permutation, using an observed auxiliary variable, such as time or a condition label, associated with changes in transition-noise distributions. Based on these results, we propose iCReN, a framework that uses contrastive learning with discrete or continuous auxiliary variables to learn latent representations and estimate their instantaneous and lagged causal structures. Experiments demonstrate accurate recovery of latent states and both instantaneous and lagged causal structures on synthetic data and the utility of the learned representations for downstream forecasting on real-world data.
