Exploiting the Prior of Generative Time Series Imputation

TL;DR

This paper introduces Bridge-TS, a novel generative time series imputation method that leverages expert and compositional priors from pretrained models to significantly improve imputation accuracy across various datasets.

Contribution

The paper proposes a new data-to-data generative approach for time series imputation that exploits expert and compositional priors, enhancing accuracy over existing methods.

Findings

Achieves state-of-the-art imputation accuracy on benchmark datasets.

Demonstrates the effectiveness of prior exploitation in generative models.

Outperforms previous methods in mean square and mean absolute error metrics.

Abstract

Time series imputation, i.e., filling the missing values of a time recording, finds various applications in electricity, finance, and weather modelling. Previous methods have introduced generative models such as diffusion probabilistic models and Schrodinger bridge models to conditionally generate the missing values from Gaussian noise or directly from linear interpolation results. However, as their prior is not informative to the ground-truth target, their generation process inevitably suffer increased burden and limited imputation accuracy. In this work, we present Bridge-TS, building a data-to-data generation process for generative time series imputation and exploiting the design of prior with two novel designs. Firstly, we propose expert prior, leveraging a pretrained transformer-based module as an expert to fill the missing values with a deterministic estimation, and then taking the results as the prior of ground truth target. Secondly, we explore compositional priors, utilizing several pretrained models to provide different estimation results, and then combining them in the data-to-data generation process to achieve a compositional priors-to-target imputation process. Experiments conducted on several benchmark datasets such as ETT, Exchange, and Weather show that Bridge-TS reaches a new record of imputation accuracy in terms of mean square error and mean absolute error, demonstrating the superiority of improving prior for generative time series imputation.