mlsanityData to 7 Oct 2026

Neural Spatiotemporal Point Processes: Trends and Challenges

arXiv 2502.09341 ↗First posted 13 Feb 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibit intricate dependencies and heterogeneous dynamics. By incorporating modern deep learning techniques, STPPs can model these complexities more effectively than traditional approaches. Consequently, the fusion of neural methods with STPPs has become an active and rapidly evolving research area. In this review, we categorize existing approaches, unify key design choices, and explain the challenges of working with this data modality. We further highlight emerging trends and diverse application domains. Finally, we identify open challenges and gaps in the literature.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 55 of its 111 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

55 of 111 references.

References · 55

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2019Invariant Risk Minimizationcited by 1,832
  6. 2020Transformer Hawkes Processcited by 230
  7. 2019Neural Jump Stochastic Differential Equationscited by 147
  8. 2019Intensity-Free Learning of Temporal Point Processescited by 138
  9. 2020Uncertainty Quantification and Deep Ensemblescited by 138
  10. 2019Fully Neural Network based Model for General Temporal Point Processescited by 119
  11. 2021Neural Temporal Point Processes: A Reviewcited by 113
  12. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 99
38 more
  1. 2017Runaway Feedback Loops in Predictive Policingcited by 97
  2. 2020Neural Spatio-Temporal Point Processescited by 92
  3. 2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 63
  4. 2024ContiFormer: Continuous-Time Transformer for Irregular Time Series Modelingcited by 61
  5. 2023Spatio-temporal Diffusion Point Processescited by 52
  6. 2017Wasserstein Learning of Deep Generative Point Process Modelscited by 46
  7. 2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
  8. 2021Neural Point Process for Learning Spatiotemporal Event Dynamicscited by 42
  9. 2017A Review of Self-Exciting Spatio-Temporal Point Processes and Their Applicationscited by 40
  10. 2018Lecture Notes: Temporal Point Processes and the Conditional Intensity Functioncited by 40
  11. 2018Learning Temporal Point Processes via Reinforcement Learningcited by 40
  12. 2020CAUSE: Learning Granger Causality from Event Sequences using Attribution Methodscited by 36
  13. 2018Deep Reinforcement Learning of Marked Temporal Point Processescited by 32
  14. 2022Exploring Generative Neural Temporal Point Processcited by 30
  15. 2019Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Informationcited by 24
  16. 2022Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processescited by 23
  17. 2023Add and Thin: Diffusion for Temporal Point Processescited by 22
  18. 2016Quantifying the vanishing gradient and long distance dependency problem in recursive neural networks and recursive LSTMscited by 21
  19. 2021Counterfactual Temporal Point Processescited by 20
  20. 2022Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Mediacited by 20
  21. 2022Statistical Deep Learning for Spatial and Spatio-Temporal Datacited by 15
  22. 2024Decomposable Transformer Point Processescited by 15
  23. 2020Causal Inference with Spatio-temporal Data: Estimating the Effects of Airstrikes on Insurgent Violence in Iraqcited by 14
  24. 2023Automatic Integration for Spatiotemporal Neural Point Processescited by 13
  25. 2023Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Predictioncited by 13
  26. 2020Spatio-Temporal Point Processes with Attention for Traffic Congestion Event Modelingcited by 12
  27. 2024Unlocking Point Processes through Point Set Diffusioncited by 12
  28. 2024Interpretable Transformer Hawkes Processes: Unveiling Complex Interactions in Social Networkscited by 11
  29. 2021Neural Spectral Marked Point Processescited by 10
  30. 2021An Empirical Study: Extensive Deep Temporal Point Processcited by 10
  31. 2023Spatio-temporal neural structural causal models for bike flow predictioncited by 9
  32. 2022Spatio-temporal point processes with deep non-stationary kernelscited by 8
  33. 2023Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processescited by 8
  34. 2022Spatio-Temporal Wildfire Prediction using Multi-Modal Datacited by 6
  35. 2024Neuro-Symbolic Temporal Point Processescited by 6
  36. 2016Impartial Predictive Modeling and the Use of Proxy Variablescited by 5
  37. 2024TransFeat-TPP: An Interpretable Deep Covariate Temporal Point Processescited by 5
  38. 2023Deep graph kernel point processes over networkscited by 4

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Deep spatio-temporal point processes: Advances and new directionscited by 1
  2. 2026HawkesNest: A Multi-Axis Synthetic Benchmark for Spatiotemporal Pattern Complexitycited by 1
  3. 2026Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modelingcited by 0
  4. 2026From Jumps to Signatures: a Generative Method for Temporal Point Processescited by 0
  5. 2026Manifold Constrained Conformal Prediction for Spatial Eventscited by 0