mlsanityData to 7 Oct 2026

Intensity-Free Learning of Temporal Point Processes

arXiv 1909.12127 ↗First posted 26 Sep 2019cs.LG stat.MLcited by 138

Not on the map. Why?

Abstract (arXiv)

Temporal point processes are the dominant paradigm for modeling sequences of events happening at irregular intervals. The standard way of learning in such models is by estimating the conditional intensity function. However, parameterizing the intensity function usually incurs several trade-offs. We show how to overcome the limitations of intensity-based approaches by directly modeling the conditional distribution of inter-event times. We draw on the literature on normalizing flows to design models that are flexible and efficient. We additionally propose a simple mixture model that matches the flexibility of flow-based models, but also permits sampling and computing moments in closed form. The proposed models achieve state-of-the-art performance in standard prediction tasks and are suitable for novel applications, such as learning sequence embeddings and imputing missing data.

Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 16; 2023: 36; 2024: 30; 2025: 23; 2026: 18.

138 papers.

Sort:

By area:

  1. 2021Neural Temporal Point Processes: A Reviewcited by 113
  2. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 99
  3. 2021Transformer Embeddings of Irregularly Spaced Events and Their Participantscited by 90
  4. 2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 63
  5. 2024ContiFormer: Continuous-Time Transformer for Irregular Time Series Modelingcited by 61
  6. 2022HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequencescited by 57
  7. 2023Spatio-temporal Diffusion Point Processescited by 52
  8. 2023Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Eventscited by 46
  9. 2023Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoningcited by 44
  10. 2024Towards Scalable and Stable Parallelization of Nonlinear RNNscited by 38
  11. 2023Anticipatory Music Transformercited by 35
  12. 2022Exploring Generative Neural Temporal Point Processcited by 30
38 more
  1. 2022EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphscited by 27
  2. 2023Prompt-augmented Temporal Point Process for Streaming Event Sequencecited by 24
  3. 2023Add and Thin: Diffusion for Temporal Point Processescited by 22
  4. 2024Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Modelscited by 21
  5. 2021Long Horizon Forecasting With Temporal Point Processescited by 20
  6. 2023Neural Fine-Gray: Monotonic neural networks for competing riskscited by 20
  7. 2022TIGGER: Scalable Generative Modelling for Temporal Interaction Graphscited by 18
  8. 2023Meta Temporal Point Processescited by 16
  9. 2023AutoSeqRec: Autoencoder for Efficient Sequential Recommendationcited by 15
  10. 2024Decomposable Transformer Point Processescited by 15
  11. 2021VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Mediacited by 14
  12. 2022Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequencescited by 14
  13. 2023On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Datacited by 13
  14. 2023Automatic Integration for Spatiotemporal Neural Point Processescited by 13
  15. 2023Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Predictioncited by 13
  16. 2021Region Invariant Normalizing Flows for Mobility Transfercited by 12
  17. 2022Parameter-free Dynamic Graph Embedding for Link Predictioncited by 12
  18. 2023Triple Structural Information Modelling for Accurate, Explainable and Interactive Recommendationcited by 12
  19. 2024Unlocking Point Processes through Point Set Diffusioncited by 12
  20. 2022ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequencescited by 11
  21. 2023A Survey on Deep Learning Techniques for Action Anticipationcited by 11
  22. 2024HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?cited by 11
  23. 2021An Empirical Study: Extensive Deep Temporal Point Processcited by 10
  24. 2023Memory Efficient Neural Processes via Constant Memory Attention Blockcited by 9
  25. 2023Interacting Diffusion Processes for Event Sequence Forecastingcited by 9
  26. 2024Latent Logic Tree Extraction for Event Sequence Explanation from LLMscited by 9
  27. 2024Deep Continuous-Time State-Space Models for Marked Event Sequencescited by 9
  28. 2023Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processescited by 8
  29. 2024Revisiting Synthetic Human Trajectories: Imitative Generation and Benchmarks Beyond Datasauruscited by 8
  30. 2024TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Modelscited by 8
  31. 2024EventFlow: Forecasting Temporal Point Processes with Flow Matchingcited by 8
  32. 2022Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processescited by 7
  33. 2023Conditional Generative Modeling for High-dimensional Marked Temporal Point Processescited by 7
  34. 2023Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Predictioncited by 7
  35. 2024Distribution-Free Conformal Joint Prediction Regions for Neural Marked Temporal Point Processescited by 7
  36. 2025In-Context Learning of Temporal Point Processes with Foundation Inference Modelscited by 7
  37. 2025Edit-Based Flow Matching for Temporal Point Processescited by 7
  38. 2021Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitionscited by 6

50 most cited of 138 All 138 (JSON)