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

TL;DR

CoSTI introduces a novel consistency model-based approach for multivariate time series imputation that significantly reduces inference time while maintaining high accuracy, enabling real-time applications in critical systems.

Contribution

This work adapts Consistency Models for multivariate time series imputation, achieving faster inference without sacrificing accuracy compared to diffusion-based models.

Findings

Up to 98% reduction in imputation time.

Performance comparable to diffusion models.

Effective across multiple datasets and missing data scenarios.

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.