mlsanityData to 7 Oct 2026

HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences

arXiv 2210.01753 ↗First posted 4 Oct 2022cs.LG cs.AIcited by 57

Not on the map. Why?

Abstract (arXiv)

In this paper, we tackle the important yet under-investigated problem of making long-horizon prediction of event sequences. Existing state-of-the-art models do not perform well at this task due to their autoregressive structure. We propose HYPRO, a hybridly normalized probabilistic model that naturally fits this task: its first part is an autoregressive base model that learns to propose predictions; its second part is an energy function that learns to reweight the proposals such that more realistic predictions end up with higher probabilities. We also propose efficient training and inference algorithms for this model. Experiments on multiple real-world datasets demonstrate that our proposed HYPRO model can significantly outperform previous models at making long-horizon predictions of future events. We also conduct a range of ablation studies to investigate the effectiveness of each component of our proposed methods.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 28 of its 57 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

28 of 57 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  4. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  5. 2020Transformer Hawkes Processcited by 230
  6. 2019Intensity-Free Learning of Temporal Point Processescited by 138
  7. 2019On the Turing Completeness of Modern Neural Network Architecturescited by 129
  8. 2019Fully Neural Network based Model for General Temporal Point Processescited by 119
  9. 2018Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiencycited by 103
  10. 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
  11. 2019Real or Fake? Learning to Discriminate Machine from Human Generated Textcited by 98
  12. 2020Residual Energy-Based Models for Text Generationcited by 95
16 more
  1. 2017Modeling The Intensity Function Of Point Process Via Recurrent Neural Networkscited by 93
  2. 2021Transformer Embeddings of Irregularly Spaced Events and Their Participantscited by 90
  3. 2019Shape and Time Distortion Loss for Training Deep Time Series Forecasting Modelscited by 66
  4. 2021Trajectory Prediction with Latent Belief Energy-Based Modelcited by 60
  5. 2020Limitations of Autoregressive Models and Their Alternativescited by 54
  6. 2021What Context Features Can Transformer Language Models Use?cited by 49
  7. 2020Identifying Coordinated Accounts on Social Media through Hidden Influence and Group Behaviourscited by 46
  8. 2021Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherencecited by 45
  9. 2019Imputing Missing Events in Continuous-Time Event Streamscited by 43
  10. 2020Neural Temporal Point Processes For Modelling Electronic Health Recordscited by 39
  11. 2019Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patternscited by 22
  12. 2020Noise-Contrastive Estimation for Multivariate Point Processescited by 20
  13. 2021Long Horizon Forecasting With Temporal Point Processescited by 20
  14. 2020User-Dependent Neural Sequence Models for Continuous-Time Event Datacited by 17
  15. 2020Neural Datalog Through Time: Informed Temporal Modeling via Logical Specificationcited by 10
  16. 2017Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 19; 2025: 17; 2026: 6.

57 papers.

Sort:

By area:

  1. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  2. 2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 63
  3. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  4. 2023Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoningcited by 44
  5. 2023Prompt-augmented Temporal Point Process for Streaming Event Sequencecited by 24
  6. 2024Decomposable Transformer Point Processescited by 15
  7. 2024HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?cited by 11
  8. 2023Interacting Diffusion Processes for Event Sequence Forecastingcited by 9
  9. 2024Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Modelscited by 9
  10. 2024Deep Continuous-Time State-Space Models for Marked Event Sequencescited by 9
  11. 2024EventFlow: Forecasting Temporal Point Processes with Flow Matchingcited by 8
  12. 2023Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Predictioncited by 7
38 more
  1. 2025In-Context Learning of Temporal Point Processes with Foundation Inference Modelscited by 7
  2. 2024Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matchingcited by 5
  3. 2024Is Score Matching Suitable for Estimating Point Processes?cited by 5
  4. 2025Byte-token Enhanced Language Models for Temporal Point Processes Analysiscited by 5
  5. 2023SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchiescited by 4
  6. 2024PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methodscited by 4
  7. 2025LAST SToP For Modeling Asynchronous Time Seriescited by 4
  8. 2024ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planningcited by 3
  9. 2023Deep Optimal Timing Strategies for Time Seriescited by 2
  10. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  11. 2023Probabilistic Modeling for Sequences of Sets in Continuous-Timecited by 2
  12. 2025Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approachescited by 2
  13. 2025TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decodingcited by 2
  14. 2025DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scalecited by 2
  15. 2024Adaptive Learning on User Segmentation: Universal to Specific Representation via Bipartite Neural Interactioncited by 1
  16. 2024A Bayesian Mixture Model of Temporal Point Processes with Determinantal Point Process Priorcited by 1
  17. 2025ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processescited by 1
  18. 2025Still Competitive: Revisiting Recurrent Models for Irregular Time Series Predictioncited by 1
  19. 2023Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inferencecited by 0
  20. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  21. 2023Explainable History Distillation by Marked Temporal Point Processcited by 0
  22. 2023GMTR: Graph Matching Transformerscited by 0
  23. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  24. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  25. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  26. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  27. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  28. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  29. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  30. 2024Unsupervised Event Outlier Detection in Continuous Timecited by 0
  31. 2025Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospectscited by 0
  32. 2025Learning Structure-enhanced Temporal Point Processes with Gromov-Wasserstein Regularizationcited by 0
  33. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  34. 2025Edge Selection for the Effective use of Piecewise-Constant Distributions as Neural Network Outputs for Event Predictioncited by 0
  35. 2025Unified Flow Matching for Long Horizon Event Forecastingcited by 0
  36. 2025MOCHA: Discovering Multi-Order Dynamic Causality in Temporal Point Processescited by 0
  37. 2025Speculative Sampling for Parametric Temporal Point Processescited by 0
  38. 2025Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processescited by 0

50 most cited of 57 All 57 (JSON)