mlsanityData to 14 Oct 2026

Add and Thin: Diffusion for Temporal Point Processes

arXiv 2311.01139 ↗First posted 2 Nov 2023cs.LG stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

Autoregressive neural networks within the temporal point process (TPP) framework have become the standard for modeling continuous-time event data. Even though these models can expressively capture event sequences in a one-step-ahead fashion, they are inherently limited for long-term forecasting applications due to the accumulation of errors caused by their sequential nature. To overcome these limitations, we derive ADD-THIN, a principled probabilistic denoising diffusion model for TPPs that operates on entire event sequences. Unlike existing diffusion approaches, ADD-THIN naturally handles data with discrete and continuous components. In experiments on synthetic and real-world datasets, our model matches the state-of-the-art TPP models in density estimation and strongly outperforms them in forecasting.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 2 Nov 2023.

Builds on

36 of 50 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  6. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  7. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  8. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  9. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  10. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  11. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  12. 2020Transformer Hawkes Processcited by 235
24 more
  1. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 216
  2. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  3. 2015On Wasserstein Two Sample Testing and Related Families of Nonparametric Testscited by 166
  4. 2019Neural Jump Stochastic Differential Equationscited by 150
  5. 2019Intensity-Free Learning of Temporal Point Processescited by 140
  6. 2019Fully Neural Network based Model for General Temporal Point Processescited by 122
  7. 2021Neural Temporal Point Processes: A Reviewcited by 114
  8. 2022CARD: Classification and Regression Diffusion Modelscited by 103
  9. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  10. 2020Neural Spatio-Temporal Point Processescited by 93
  11. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 88
  12. 2020Identifying Coordinated Accounts on Social Media through Hidden Influence and Group Behaviourscited by 47
  13. 2017Wasserstein Learning of Deep Generative Point Process Modelscited by 46
  14. 2018Learning Temporal Point Processes via Reinforcement Learningcited by 40
  15. 2020Neural Temporal Point Processes For Modelling Electronic Health Recordscited by 39
  16. 2022Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusioncited by 39
  17. 2020CAUSE: Learning Granger Causality from Event Sequences using Attribution Methodscited by 36
  18. 2020Fast and Flexible Temporal Point Processes with Triangular Mapscited by 30
  19. 2022Exploring Generative Neural Temporal Point Processcited by 30
  20. 2019Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Informationcited by 24
  21. 2023Learning to Jump: Thinning and Thickening Latent Counts for Generative Modelingcited by 18
  22. 2023On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Datacited by 14
  23. 2021Deep Neyman-Scott Processescited by 6
  24. 2023Inference and Sampling of Point Processes from Diffusion Excursionscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 12; 2026: 7.

23 papers.

Sort:

By area:

  1. 2024Unlocking Point Processes through Point Set Diffusioncited by 14
  2. 2024HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?cited by 13
  3. 2025In-Context Learning of Temporal Point Processes with Foundation Inference Modelscited by 10
  4. 2024EventFlow: Forecasting Temporal Point Processes with Flow Matchingcited by 8
  5. 2025Edit-Based Flow Matching for Temporal Point Processescited by 8
  6. 2025LAST SToP For Modeling Asynchronous Time Seriescited by 5
  7. 2025Neural Spatiotemporal Point Processes: Trends and Challengescited by 5
  8. 2024Unfolding Time: Generative Modeling for Turbulent Flows in 4Dcited by 4
  9. 2025Generative Modeling with Bayesian Sample Inferencecited by 4
  10. 2025Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approachescited by 3
  11. 2025Generative Unordered Flow for Set-Structured Data Generationcited by 2
  12. 2025ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processescited by 2
11 more
  1. 2025Deep spatio-temporal point processes: Advances and new directionscited by 1
  2. 2026ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Seriescited by 1
  3. 2025Edge Selection for the Effective use of Piecewise-Constant Distributions as Neural Network Outputs for Event Predictioncited by 0
  4. 2025Speculative Sampling for Parametric Temporal Point Processescited by 0
  5. 2025Addressing Mark Imbalance in Integration-free Neural Marked Temporal Point Processescited by 0
  6. 2026Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Eventscited by 0
  7. 2026On Observation Time for Recovering Latent Hawkes Networkscited by 0
  8. 2026Structured Neural Marked Point Processes for Interpretable Event Interaction Modelingcited by 0
  9. 2026Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generationcited by 0
  10. 2026From Jumps to Signatures: a Generative Method for Temporal Point Processescited by 0
  11. 2026Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Interacting Diffusion Processes for Event Sequence Forecasting
  2. 2023Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Prediction
  3. 2025Non-stationary Diffusion For Probabilistic Time Series Forecasting
  4. 2025SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecasting
  5. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
  6. 2026When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Version
  7. 2024TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
  8. 2024The Rise of Diffusion Models in Time-Series Forecasting