Time Series Domain Adaptation via Latent Invariant Causal Mechanism

TL;DR

This paper introduces a novel framework for time series domain adaptation that models latent causal mechanisms to improve transferability across domains, especially in high-dimensional data like videos.

Contribution

It proposes a latent causal mechanism identification framework with guarantees of uniqueness and develops the Latent Causality Alignment (LCA) model using variational inference for domain-invariant structure learning.

Findings

Improved domain-adaptive time series classification and forecasting results.

Effective latent causal structure reconstruction across domains.

Demonstrated robustness on eight benchmark datasets.

Abstract

Time series domain adaptation aims to transfer the complex temporal dependence from the labeled source domain to the unlabeled target domain. Recent advances leverage the stable causal mechanism over observed variables to model the domain-invariant temporal dependence. However, modeling precise causal structures in high-dimensional data, such as videos, remains challenging. Additionally, direct causal edges may not exist among observed variables (e.g., pixels). These limitations hinder the applicability of existing approaches to real-world scenarios. To address these challenges, we find that the high-dimension time series data are generated from the low-dimension latent variables, which motivates us to model the causal mechanisms of the temporal latent process. Based on this intuition, we propose a latent causal mechanism identification framework that guarantees the uniqueness of the reconstructed latent causal structures. Specifically, we first identify latent variables by utilizing sufficient changes in historical information. Moreover, by enforcing the sparsity of the relationships of latent variables, we can achieve identifiable latent causal structures. Built on the theoretical results, we develop the Latent Causality Alignment (LCA) model that leverages variational inference, which incorporates an intra-domain latent sparsity constraint for latent structure reconstruction and an inter-domain latent sparsity constraint for domain-invariant structure reconstruction. Experiment results on eight benchmarks show a general improvement in the domain-adaptive time series classification and forecasting tasks, highlighting the effectiveness of our method in real-world scenarios. Codes are available at https://github.com/DMIRLAB-Group/LCA.