mlsanityData to 7 Oct 2026

DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis

arXiv 2401.04979 ↗First posted 10 Jan 2024cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Real-world time series analysis faces significant challenges when dealing with irregular and incomplete data. While Neural Differential Equation (NDE) based methods have shown promise, they struggle with limited expressiveness, scalability issues, and stability concerns. Conversely, Neural Flows offer stability but falter with irregular data. We introduce 'DualDynamics', a novel framework that synergistically combines NDE-based method and Neural Flow-based method. This approach enhances expressive power while balancing computational demands, addressing critical limitations of existing techniques. We demonstrate DualDynamics' effectiveness across diverse tasks: classification of robustness to dataset shift, irregularly-sampled series analysis, interpolation of missing data, and forecasting with partial observations. Our results show consistent outperformance over state-of-the-art methods, indicating DualDynamics' potential to advance irregular time series analysis significantly.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 42 of its 62 references that are in the map. First posted on arXiv 10 Jan 2024.

Builds on

42 of 62 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  8. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  9. 2018DeepMind Control Suitecited by 935
  10. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  11. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  12. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
30 more
  1. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  2. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  3. 2018The UCR Time Series Archivecited by 421
  4. 2019Augmented Neural ODEscited by 396
  5. 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
  6. 2018Invertible Residual Networkscited by 364
  7. 2018The UEA multivariate time series classification archive, 2018cited by 330
  8. 2020Scalable Gradients for Stochastic Differential Equationscited by 264
  9. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 234
  10. 2019GRU-ODE-Bayes: Continuous modeling of sporadically-observed time seriescited by 230
  11. 2015Doctor AI: Predicting Clinical Events via Recurrent Neural Networkscited by 205
  12. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  13. 2020Dissecting Neural ODEscited by 150
  14. 2019Neural Jump Stochastic Differential Equationscited by 147
  15. 2020OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transportcited by 143
  16. 2020Neural Rough Differential Equations for Long Time Seriescited by 140
  17. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 99
  18. 2019sktime: A Unified Interface for Machine Learning with Time Seriescited by 98
  19. 2020Learning Long-Term Dependencies in Irregularly-Sampled Time Seriescited by 82
  20. 2021Neural ODE Processescited by 57
  21. 2020"Hey, that's not an ODE": Faster ODE Adjoints via Seminormscited by 35
  22. 2021Attentive Neural Controlled Differential Equations for Time-series Classification and Forecastingcited by 28
  23. 2020Stable Neural Flowscited by 25
  24. 2015Large-scale Log-determinant Computation through Stochastic Chebyshev Expansionscited by 17
  25. 2021ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equationscited by 15
  26. 2022Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rulescited by 15
  27. 2019Time series classification for varying length seriescited by 10
  28. 2023Learnable Path in Neural Controlled Differential Equationscited by 8
  29. 2018Efficient Discovery of Variable-length Time Series Motifs with Large Length Range in Million Scale Time Seriescited by 3
  30. 2023Incremental Neural Controlled Differential Equations for Modeling of Path-dependent Material Behaviorcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Comprehensive Review of Neural Differential Equations for Time Series Analysiscited by 20
  2. 2026One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classificationcited by 1
  3. 2026Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Predictioncited by 0
  4. 2026Rarity-Gated Context Conditioning for Offline Imitation Learning-Based Maritime Anomaly Detectioncited by 0