Frequency-aware Generative Models for Multivariate Time Series Imputation

Xinyu Yang, Yu Sun, Xiaojie Yuan, Xinyang Chen

Keywords: Time series; Time series Imputation; Generative Models; Frequency domain

TL;DR: This paper proposes a frequency-aware generative model (FGTI) for multivariate time series imputation, which integrates frequency-domain information and uses cross-domain representation learning modules to enhance imputation accuracy.

Abstract:

Missing data in multivariate time series are common issues that can affect the analysis and downstream applications.
Although multivariate time series data generally consist of the trend, seasonal and residual terms, existing works mainly focus on optimizing the modeling for the first two items. However, we find that the residual term is more crucial for getting accurate fillings, since it is more related to the diverse changes of data and the biggest component of imputation errors.
Therefore, in this study, we introduce frequency-domain information and design Frequency-aware Generative Models for Multivariate Time Series Imputation (FGTI). Specifically, FGTI employs a high-frequency filter to boost the residual term imputation, supplemented by a dominant-frequency filter for the trend and seasonal imputation. Cross-domain representation learning module then fuses frequency-domain insights with deep representations.
Experiments over various datasets with real-world missing values show that FGTI achieves superiority in both data imputation and downstream applications.

Primary Area: Machine learning for other sciences and fields

Submission Number: 15880