SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation

TL;DR

This paper introduces SSD-TS, a novel approach combining linear state space models with diffusion models to improve probabilistic time series imputation, addressing efficiency and dependency modeling challenges.

Contribution

It proposes using the Mamba state space model as the backbone for diffusion models, along with new SSM-based blocks for better time series dependency handling.

Findings

Achieves state-of-the-art imputation accuracy on multiple datasets.

Demonstrates improved efficiency over traditional methods.

Effectively models complex temporal dependencies.

Abstract

Probabilistic time series imputation has been widely applied in real-world scenarios due to its ability for uncertainty estimation and denoising diffusion probabilistic models~(DDPMs) have achieved great success in probabilistic time series imputation tasks with its power to model complex distributions. However, current DDPM-based probabilistic time series imputation methodologies are confronted with two types of challenges: 1)\textit{The backbone modules of the denoising parts are not capable of achieving sequence modeling with low time complexity.} 2)~\textit{The architecture of denoising modules can not handle the dependencies in the time series data effectively.} To address the first challenge, we explore the potential of state space model, namely Mamba, as the backbone denoising module for DDPMs. To tackle the second challenge, we carefully devise several SSM-based blocks for time series data modeling. Experimental results demonstrate that our approach can achieve state-of-the-art time series imputation results on multiple real-world datasets. Our datasets and code are available at \href{https://github.com/decisionintelligence/SSD-TS/}{https://github.com/decisionintelligence/SSD-TS/}