Saved in:
Bibliographic Details
Main Authors: Gao, Hongfan, Shen, Wangmeng, Qiu, Xiangfei, Xu, Ronghui, Hu, Jilin, Yang, Bin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.13338
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908493725827072
author Gao, Hongfan
Shen, Wangmeng
Qiu, Xiangfei
Xu, Ronghui
Hu, Jilin
Yang, Bin
author_facet Gao, Hongfan
Shen, Wangmeng
Qiu, Xiangfei
Xu, Ronghui
Hu, Jilin
Yang, Bin
contents 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/}
format Preprint
id arxiv_https___arxiv_org_abs_2410_13338
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation
Gao, Hongfan
Shen, Wangmeng
Qiu, Xiangfei
Xu, Ronghui
Hu, Jilin
Yang, Bin
Machine Learning
Artificial Intelligence
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/}
title SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.13338