CoSTI: Consistency Models for (a faster) Spatio-Temporal Imputation

Abstract

Multivariate Time Series Imputation (MTSI) is crucial for many applications, such as healthcare monitoring and traffic management, where incomplete data can compromise decision-making. Existing state-of-the-art methods, like Denoising Diffusion Probabilistic Models (DDPMs), achieve high imputation accuracy; however, they suffer from significant computational costs and are notably time-consuming due to their iterative nature. In this work, we propose CoSTI, an innovative adaptation of Consistency Models (CMs) for the MTSI domain. CoSTI employs Consistency Training to achieve comparable imputation quality to DDPMs while drastically reducing inference times, making it more suitable for real-time applications. We evaluate CoSTI across multiple datasets and missing data scenarios, demonstrating up to a 98% reduction in imputation time with performance on par with diffusion-based models. This work bridges the gap between efficiency and accuracy in generative imputation tasks, providing a scalable solution for handling missing data in critical spatio-temporal systems.

arXiv comment14 pages, 7 figures, 13 tables

References in corpus (7)

• Array Programming with NumPy
• Denoising Diffusion Probabilistic Models
• BRITS: Bidirectional Recurrent Imputation for Time Series
• Elucidating the Design Space of Diffusion-Based Generative Models
• Modeling Missing Data in Clinical Time Series with RNNs
• Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models
• A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification