基于长程依赖扩散模型的边界增强时间序列数据插补
Boundary-enhanced time series data imputation with long-term dependency diffusion models
AI总结：
针对现有扩散模型时间序列插补存在的边界不协调、忽略长程依赖的问题，提出DSDI框架，通过权重递减注入策略和多尺度S4 U-Net实现更优的插补效果。
摘要：
数据插补对于解决医疗、交通、经济等各领域多变量时间序列数据中缺失值带来的挑战至关重要，已受到广泛关注。在各类方法中，基于扩散模型的方法表现出显著的性能提升。然而，现有方法往往会导致缺失区域与已知区域之间的边界不协调，且在缺失数据估计中忽略了长程依赖，导致结果欠佳。为解决这些问题，我们提出了基于扩散的时间序列数据插补（Diffusion-based time Series Data Imputation，DSDI）框架。我们设计了一种权重递减注入策略，将权重逐步降低的缺失点预测值纳入反向扩散过程，以缓解边界不一致问题。此外，我们引入了基于多尺度S4的U-Net，通过多分辨率整合结合不同层级的分层信息以捕捉长程依赖。实验结果表明，我们的模型性能优于现有插补方法。
英文摘要：
Data imputation is crucial for addressing challenges posed by missing values in multivariate time series data across various fields, such as healthcare, traffic, and economics, and has garnered significant attention. Among various methods, diffusion model-based approaches show notable performance improvements. However, existing methods often cause disharmonious boundaries between missing and known regions and overlook long-range dependencies in missing data estimation, leading to suboptimal results. To address these issues, we propose a Diffusion-based time Series Data Imputation (DSDI) framework. We develop a weight-reducing injection strategy that incorporates the predicted values of missing points with reducing weights into the reverse diffusion process to mitigate boundary inconsistencies. Further, we introduce a multi-scale S4-based U-Net, which combines hierarchical information from different levels via multi-resolution integration to capture long-term dependencies. Experimental results demonstrate that our model outperforms existing imputation methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
