Xiao, Chunjing; Jiang, Xue; Du, Xianghe; Yang, Wei; Lu, Wei; Wang, Xiaomin; Chetty, Kevin; (2024) Boundary-enhanced time series data imputation with long-term dependency diffusion models. Knowledge-Based Systems , Article 112917. 10.1016/j.knosys.2024.112917. (In press).

Text pre-proof.pdf - Accepted Version Access restricted to UCL open access staff until 31 December 2025. Download (975kB)

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.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item