mlsanityData to 7 Oct 2026

GP-VAE: Deep Probabilistic Time Series Imputation

arXiv 1907.04155 ↗First posted 9 Jul 2019stat.ML cs.LGcited by 171

Not on the map. Why?

Cited by 32 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Multivariate time series with missing values are common in areas such as healthcare and finance, and have grown in number and complexity over the years. This raises the question whether deep learning methodologies can outperform classical data imputation methods in this domain. However, naive applications of deep learning fall short in giving reliable confidence estimates and lack interpretability. We propose a new deep sequential latent variable model for dimensionality reduction and data imputation. Our modeling assumption is simple and interpretable: the high dimensional time series has a lower-dimensional representation which evolves smoothly in time according to a Gaussian process. The non-linear dimensionality reduction in the presence of missing data is achieved using a VAE approach with a novel structured variational approximation. We demonstrate that our approach outperforms several classical and deep learning-based data imputation methods on high-dimensional data from the domains of computer vision and healthcare, while additionally improving the smoothness of the imputations and providing interpretable uncertainty estimates.

Key facts. Cited by 171 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 17; 2023: 32; 2024: 40; 2025: 37; 2026: 31.

171 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  3. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  4. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 167
  5. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  6. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  7. 2022DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Renderingcited by 80
  8. 2023Diffusion Models for Time Series Applications: A Surveycited by 72
  9. 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 65
  10. 2023PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputationcited by 62
  11. 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
  12. 2022Neural Diffusion Processescited by 50
38 more
  1. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  2. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Seriescited by 42
  3. 2022Deep Latent State Space Models for Time-Series Generationcited by 37
  4. 2023GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputationcited by 35
  5. 2021Missing Value Imputation on Multidimensional Time Seriescited by 33
  6. 2024TSI-Bench: Benchmarking Time Series Imputationcited by 33
  7. 2023Autoregressive Conditional Neural Processescited by 32
  8. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  9. 2024On the Challenges and Opportunities in Generative AIcited by 31
  10. 2023Deep Imputation of Missing Values in Time Series Health Data: A Review with Benchmarkingcited by 29
  11. 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputationcited by 26
  12. 2023Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Modelscited by 22
  13. 2023Probabilistic Imputation for Time-series Classification with Missing Datacited by 21
  14. 2024GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missingcited by 20
  15. 2024SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputationcited by 18
  16. 2022Decoupling Local and Global Representations of Time Seriescited by 17
  17. 2022Markovian Gaussian Process Variational Autoencoderscited by 16
  18. 2023TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Seriescited by 16
  19. 2023Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representationscited by 16
  20. 2022Retrieval Based Time Series Forecastingcited by 13
  21. 2024MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputationcited by 13
  22. 2021PriorVAE: Encoding spatial priors with VAEs for small-area estimationcited by 11
  23. 2022Learning Conditional Variational Autoencoders with Missing Covariatescited by 10
  24. 2024TimeLDM: Latent Diffusion Model for Unconditional Time Series Generationcited by 10
  25. 2021Spatiotemporal Tensor Completion for Improved Urban Traffic Imputationcited by 9
  26. 2023Fully Bayesian Autoencoders with Latent Sparse Gaussian Processescited by 9
  27. 2023DiffECG: A Versatile Probabilistic Diffusion Model for ECG Signals Synthesiscited by 9
  28. 2023BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decompositioncited by 9
  29. 2023Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Datacited by 9
  30. 2025Glocal Information Bottleneck for Time Series Imputationcited by 9
  31. 2021Learning Disentangled Representations for Time Seriescited by 8
  32. 2024Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarkingcited by 8
  33. 2025LSCD: Lomb-Scargle Conditioned Diffusion for Time series Imputationcited by 8
  34. 2025From Samples to Scenarios: A New Paradigm for Probabilistic Forecastingcited by 8
  35. 2021Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparisoncited by 7
  36. 2021Gradient Importance Learning for Incomplete Observationscited by 7
  37. 2024Review for Handling Missing Data with special missing mechanismcited by 7
  38. 2024Sequential Disentanglement by Extracting Static Information From A Single Sequence Elementcited by 7

50 most cited of 171 All 171 (JSON)