DiffImp: Efficient Diffusion Model for Probabilistic Time Series Imputation with Bidirectional Mamba Backbone
원문 초록
Probabilistic time series imputation has been widely applied in real-world scenarios due to its ability to estimate uncertainty of imputation results. Meanwhile, 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 inter-variable and bidirectional dependencies in the time series imputation problem effectively.} To address the first challenge, we integrate the computational efficient state space model, namely Mamba, as the backbone denosing module for DDPMs. To tackle the second challenge, we carefully devise several SSM-based blocks for bidirectional modeling and inter-variable relation understanding. Experimental results demonstrate that our approach can achieve state-of-the-art time series imputation results on multiple datasets, different missing scenarios and missing ratios.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Cross-Domain Conditional Diffusion Models for Time Series Imputation
LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
KARMA: A Multilevel Decomposition Hybrid Mamba Framework for Multivariate Long-Term Time Series Forecasting
MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modeling
Time-series surrogates from energy consumers generated by machine learning approaches for long-term forecasting scenarios
토론
이 논문과 연결된 포럼 글이 아직 없습니다.