mlsanityData to 14 Oct 2026

GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series

arXiv 1905.12374 ↗First posted 29 May 2019cs.LG stat.MLcited by 231

Not on the map. Why?

Abstract (arXiv)

Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed (i.e., sampling is irregular both in time and across dimensions)-such as in the case of clinical patient data. To address these challenges, we propose (1) a continuous-time version of the Gated Recurrent Unit, building upon the recent Neural Ordinary Differential Equations (Chen et al., 2018), and (2) a Bayesian update network that processes the sporadic observations. We bring these two ideas together in our GRU-ODE-Bayes method. We then demonstrate that the proposed method encodes a continuity prior for the latent process and that it can exactly represent the Fokker-Planck dynamics of complex processes driven by a multidimensional stochastic differential equation. Additionally, empirical evaluation shows that our method outperforms the state of the art on both synthetic data and real-world data with applications in healthcare and climate forecast. What is more, the continuity prior is shown to be well suited for low number of samples settings.

Key facts. Cited by 231 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 32; 2022: 38; 2023: 39; 2024: 36; 2025: 40; 2026: 46.

231 papers.

Sort:

By area:

  1. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  2. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  3. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  4. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
  5. 2022Liquid Structural State-Space Modelscited by 136
  6. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 120
  7. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
  8. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 101
  9. 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEscited by 82
  10. 2021Efficient and Accurate Gradients for Neural SDEscited by 71
  11. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  12. 2021Neural ODE Processescited by 57
38 more
  1. 2025Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baselinecited by 55
  2. 2021Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progressioncited by 48
  3. 2021Neural Controlled Differential Equations for Online Prediction Taskscited by 46
  4. 2022GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networkscited by 44
  5. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Seriescited by 43
  6. 2021Neural Point Process for Learning Spatiotemporal Event Dynamicscited by 42
  7. 2021Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equationscited by 38
  8. 2022Deep Latent State Space Models for Time-Series Generationcited by 38
  9. 2024Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Datacited by 36
  10. 2021Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Seriescited by 30
  11. 2021Attentive Neural Controlled Differential Equations for Time-series Classification and Forecastingcited by 29
  12. 2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Seriescited by 29
  13. 2021Auto-differentiable Ensemble Kalman Filterscited by 28
  14. 2022Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Datacited by 27
  15. 2022Efficient recurrent architectures through activity sparsity and sparse back-propagation through timecited by 26
  16. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  17. 2023Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Modelscited by 24
  18. 2024Trajectory Flow Matching with Applications to Clinical Time Series Modelingcited by 24
  19. 2021Framing RNN as a kernel method: A neural ODE approachcited by 23
  20. 2022Predicting the impact of treatments over time with uncertainty aware neural differential equationscited by 23
  21. 2022EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecastingcited by 22
  22. 2021Climate Modeling with Neural Diffusion Equationscited by 20
  23. 2025Comprehensive Review of Neural Differential Equations for Time Series Analysiscited by 20
  24. 2022Learning Spatio-Temporal Model of Disease Progression with NeuralODEs from Longitudinal Volumetric Datacited by 19
  25. 2025Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Seriescited by 19
  26. 2021Policy Analysis using Synthetic Controls in Continuous-Timecited by 18
  27. 2023Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representationscited by 17
  28. 2022Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rulescited by 16
  29. 2021ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equationscited by 15
  30. 2024Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Seriescited by 15
  31. 2025HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecastingcited by 15
  32. 2021Learning dynamical systems from data: A simple cross-validation perspective, part III: Irregularly-Sampled Time Seriescited by 14
  33. 2023Reduced-Order Autodifferentiable Ensemble Kalman Filterscited by 14
  34. 2021Spatiotemporal Data Mining: A Survey on Challenges and Open Problemscited by 13
  35. 2023Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Predictioncited by 13
  36. 2023Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equationcited by 12
  37. 2023Graph Convolutions Enrich the Self-Attention in Transformers!cited by 11
  38. 2024Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equationscited by 11

50 most cited of 231 All 231 (JSON)