mlsanityData to 14 Oct 2026

RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting

arXiv 2106.06064 ↗First posted 10 Jun 2021stat.ML cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Spatio-temporal forecasting has numerous applications in analyzing wireless, traffic, and financial networks. Many classical statistical models often fall short in handling the complexity and high non-linearity present in time-series data. Recent advances in deep learning allow for better modelling of spatial and temporal dependencies. While most of these models focus on obtaining accurate point forecasts, they do not characterize the prediction uncertainty. In this work, we consider the time-series data as a random realization from a nonlinear state-space model and target Bayesian inference of the hidden states for probabilistic forecasting. We use particle flow as the tool for approximating the posterior distribution of the states, as it is shown to be highly effective in complex, high-dimensional settings. Thorough experimentation on several real world time-series datasets demonstrates that our approach provides better characterization of uncertainty while maintaining comparable accuracy to the state-of-the art point forecasting methods.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 45 of its 86 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

45 of 86 references.

References · 45

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  6. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  8. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  9. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  10. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  11. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  12. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
33 more
  1. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  2. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  3. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  4. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  5. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  6. 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 180
  7. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  8. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 156
  9. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 148
  10. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 144
  11. 2016Sequential Neural Models with Stochastic Layerscited by 115
  12. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  13. 2017Variational Sequential Monte Carlocited by 95
  14. 2017Filtering Variational Objectivescited by 91
  15. 2019Deep Factors for Forecastingcited by 86
  16. 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
  17. 2017Auto-Encoding Sequential Monte Carlocited by 65
  18. 2018Particle Filter Networks with Application to Visual Localizationcited by 65
  19. 2018Probabilistic Recurrent State-Space Modelscited by 64
  20. 2014Learning Stochastic Recurrent Networkscited by 60
  21. 2019STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecastingcited by 60
  22. 2019Particle Filter Recurrent Neural Networkscited by 36
  23. 2015Neural Adaptive Sequential Monte Carlocited by 34
  24. 2020FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecastingcited by 30
  25. 2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29
  26. 2018A Memory-Network Based Solution for Multivariate Time-Series Forecastingcited by 22
  27. 20193D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecastingcited by 12
  28. 2017State Space LSTM Models with Particle MCMC Inferencecited by 11
  29. 2015Recurrent Gaussian Processescited by 9
  30. 2019ST-GRAT: A Novel Spatio-temporal Graph Attention Network for Accurately Forecasting Dynamically Changing Road Speedcited by 9
  31. 2016Particle Filtering with Invertible Particle Flowcited by 5
  32. 2019Particle Flow Bayes' Rulecited by 5
  33. 2018Multi-variable LSTM neural network for autoregressive exogenous modelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 4; 2025: 3; 2026: 1.

16 papers.

Sort:

By area:

  1. 2023DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Modelscited by 81
  2. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  3. 2025Relational Conformal Prediction for Correlated Time Seriescited by 11
  4. 2022Taming the Long Tail of Deep Probabilistic Forecastingcited by 7
  5. 2023Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systemscited by 5
  6. 2024SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecastingcited by 5
  7. 2024OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learningcited by 5
  8. 2023Graph State-Space Models and Latent Relational Inferencecited by 4
  9. 2023Assessment of Spatio-Temporal Predictors in the Presence of Missing and Heterogeneous Datacited by 2
  10. 2025Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matchingcited by 2
  11. 2023Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecastingcited by 1
  12. 2024LINOCS: Lookahead Inference of Networked Operators for Continuous Stabilitycited by 1
4 more
  1. 2022Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge Distillationcited by 0
  2. 2024Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modellingcited by 0
  3. 2025Denoising Refinement Diffusion Models for Simultaneous Generation of Multi-scale Mobile Network Trafficcited by 0
  4. 2026Addressing Spatial Indistinguishability in Spatiotemporal Prediction via Optimal Transport-Guided Maskingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations
  2. 2025Probabilistic Forecasting via Autoregressive Flow Matching
  3. 2026Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecast
  4. 2025Collaborative Deterministic-Probabilistic Forecasting for Diverse Spatiotemporal Systems
  5. 2024Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting
  6. 2024Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
  7. 2026MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting
  8. 2026Variational Streaming Flow: Probabilistic Forecasting in Physical Time