Boundary-enhanced time series data imputation with long-term dependency diffusion models

Abstract

Data imputation is crucial for addressing challenges posed by missing values in multivariate time series data across various fields, such as healthcare, traffic, and economics, and has garnered significant attention. Among various methods, diffusion model-based approaches show notable performance improvements. However, existing methods often cause disharmonious boundaries between missing and known regions and overlook long-range dependencies in missing data estimation, leading to suboptimal results. To address these issues, we propose a Diffusion-based time Series Data Imputation (DSDI) framework. We develop a weight-reducing injection strategy that incorporates the predicted values of missing points with reducing weights into the reverse diffusion process to mitigate boundary inconsistencies. Further, we introduce a multi-scale S4-based U-Net, which combines hierarchical information from different levels via multi-resolution integration to capture long-term dependencies. Experimental results demonstrate that our model outperforms existing imputation methods.

Accepted by Knowledge-Based Systems

References in corpus (7)

• SAITS: Self-Attention-based Imputation for Time Series
• Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models
• MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputation
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
• Diffusion Model-based Contrastive Learning for Human Activity Recognition
• Low-Rank Autoregressive Tensor Completion for Multivariate Time Series Forecasting
• Deep Learning for Multivariate Time Series Imputation: A Survey