mlsanityData to 14 Oct 2026

Boundary-enhanced time series data imputation with long-term dependency diffusion models

arXiv 2501.06585 ↗First posted 11 Jan 2025cs.LG cs.SIcited by 2

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 29 of its 57 references that are in the map. First posted on arXiv 11 Jan 2025.

Builds on

29 of 57 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputation11 Aug
  2. 2024Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection2 Jul
  3. 2023Diffusion Models for Time Series Applications: A Survey1 May
  4. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul

Other references · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  6. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 424
  7. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  8. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  9. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  10. 2018Handling Incomplete Heterogeneous Data using VAEscited by 149
  11. 2022Long Movie Clip Classification with State-Space Video Modelscited by 106
  12. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 90
13 more
  1. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  2. 2018Gaussian Process Prior Variational Autoencoderscited by 72
  3. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  4. 2019NAOMI: Non-Autoregressive Multiresolution Sequence Imputationcited by 59
  5. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  6. 2018Leveraging the Exact Likelihood of Deep Latent Variable Modelscited by 23
  7. 2020PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Datacited by 15
  8. 2024Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Valuescited by 10
  9. 2024Higher-order Spatio-temporal Physics-incorporated Graph Neural Network for Multivariate Time Series Imputationcited by 8
  10. 2020Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networkscited by 6
  11. 2023Continuous-time Autoencoders for Regular and Irregular Time Series Imputationcited by 6
  12. 2024Mining of Switching Sparse Networks for Missing Value Imputation in Multivariate Time Seriescited by 5
  13. 2024Diffusion Model-based Contrastive Learning for Human Activity Recognitioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputationcited by 1
  2. 2026CINDI: Conditional Imputation and Noisy Data Integrity with Flows in Power Grid Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
  2. 2026Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective
  3. 2025Cross-Domain Conditional Diffusion Models for Time Series Imputation
  4. 2024Latent Space Score-based Diffusion Model for Probabilistic Multivariate Time Series Imputation
  5. 2026Discretizing Continuous Time Series for Imputation with Masked Diffusion Training
  6. 2024SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation
  7. 2026RDDMPI: Residual Denoising Diffusion Model for Probabilistic Multivariate Time Series Imputation
  8. 2025CoSTI: Consistency Models for (a faster) Spatio-Temporal Imputation