mlsanityData to 14 Oct 2026

Latent ODEs for Irregularly-Sampled Time Series

arXiv 1907.03907 ↗First posted 8 Jul 2019cs.LG stat.MLcited by 183

Not on the map. Why?

Abstract (arXiv)

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace the recognition network of the recently-proposed Latent ODE model. Both ODE-RNNs and Latent ODEs can naturally handle arbitrary time gaps between observations, and can explicitly model the probability of observation times using Poisson processes. We show experimentally that these ODE-based models outperform their RNN-based counterparts on irregularly-sampled data.

Key facts. Cited by 183 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 35; 2023: 27; 2024: 17; 2025: 25; 2026: 41.

183 papers.

Sort:

By area:

  1. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
  2. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  3. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
  4. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 101
  5. 2021Closed-form Continuous-time Neural Modelscited by 65
  6. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  7. 2021Neural ODE Processescited by 57
  8. 2022Learning Fast and Slow for Online Time Series Forecastingcited by 45
  9. 2022STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Predictioncited by 45
  10. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  11. 2021Long Expressive Memory for Sequence Modelingcited by 41
  12. 2021Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equationscited by 38
38 more
  1. 2021A Framework for Machine Learning of Model Error in Dynamical Systemscited by 38
  2. 2022Signature Methods in Machine Learningcited by 34
  3. 2021Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Seriescited by 30
  4. 2024Universal Time-Series Representation Learning: A Surveycited by 30
  5. 2021Attentive Neural Controlled Differential Equations for Time-series Classification and Forecastingcited by 29
  6. 2021Constraint-based graph network simulatorcited by 27
  7. 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputationcited by 27
  8. 2021Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristicscited by 26
  9. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  10. 2022Neural Laplace: Learning diverse classes of differential equations in the Laplace domaincited by 24
  11. 2021Causal Navigation by Continuous-time Neural Networkscited by 23
  12. 2022Predicting the impact of treatments over time with uncertainty aware neural differential equationscited by 23
  13. 2023Probabilistic Imputation for Time-series Classification with Missing Datacited by 22
  14. 2025MIRA: Medical Time Series Foundation Model for Real-World Health Datacited by 22
  15. 2023Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networkcited by 20
  16. 2021Policy Analysis using Synthetic Controls in Continuous-Timecited by 18
  17. 2023Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounderscited by 17
  18. 2023Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representationscited by 17
  19. 2023Latent SDEs on Homogeneous Spacescited by 16
  20. 2021Variational multiple shooting for Bayesian ODEs with Gaussian processescited by 15
  21. 2021Beyond Predictions in Neural ODEs: Identification and Interventionscited by 15
  22. 2021Joint inference and input optimization in equilibrium networkscited by 15
  23. 2024Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Seriescited by 15
  24. 2021Stateful ODE-Nets using Basis Function Expansionscited by 14
  25. 2021Learning dynamical systems from data: A simple cross-validation perspective, part III: Irregularly-Sampled Time Seriescited by 14
  26. 2023Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Predictioncited by 13
  27. 2021Second-Order Neural ODE Optimizercited by 11
  28. 2021An Empirical Study: Extensive Deep Temporal Point Processcited by 10
  29. 2023Neural Laplace Control for Continuous-time Delayed Systemscited by 10
  30. 2022Fractional SDE-Net: Generation of Time Series Data with Long-term Memorycited by 9
  31. 2022Path Development Network with Finite-dimensional Lie Group Representationcited by 8
  32. 2022Recognition Models to Learn Dynamics from Partial Observations with Neural ODEscited by 8
  33. 2022Non-equispaced Fourier Neural Solvers for PDEscited by 8
  34. 2023Towards Complex Dynamic Physics System Simulation with Graph Neural ODEscited by 8
  35. 2024Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Trackingcited by 8
  36. 2026ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Datacited by 8
  37. 2026Tracing Agentic Failure from the Flow of Successcited by 8
  38. 2021Continuous-Depth Neural Models for Dynamic Graph Predictioncited by 7

50 most cited of 183 All 183 (JSON)