Data to 14 Oct 2026

Transformer Hawkes Process

arXiv 2002.09291 ↗First posted 21 Feb 2020cs.LG stat.MLcited by 235

Not on the map. Why?

Abstract (arXiv)

Modern data acquisition routinely produce massive amounts of event sequence data in various domains, such as social media, healthcare, and financial markets. These data often exhibit complicated short-term and long-term temporal dependencies. However, most of the existing recurrent neural network based point process models fail to capture such dependencies, and yield unreliable prediction performance. To address this issue, we propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies and meanwhile enjoys computational efficiency. Numerical experiments on various datasets show that THP outperforms existing models in terms of both likelihood and event prediction accuracy by a notable margin. Moreover, THP is quite general and can incorporate additional structural knowledge. We provide a concrete example, where THP achieves improved prediction performance for learning multiple point processes when incorporating their relational information.

Key facts. Cited by 235 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 29; 2023: 46; 2024: 62; 2025: 34; 2026: 39.

235 papers.

Sort:

By area:

2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
2022Transformers in Time Series: A Surveycited by 497
2021Neural Temporal Point Processes: A Reviewcited by 114
2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
2021Transformer Embeddings of Irregularly Spaced Events and Their Participantscited by 93
2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 68
2024ContiFormer: Continuous-Time Transformer for Irregular Time Series Modelingcited by 63
2023A Unified, Scalable Framework for Neural Population Decodingcited by 61
2022HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequencescited by 57
2024Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Reviewcited by 53
2023Spatio-temporal Diffusion Point Processescited by 52
2023Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Eventscited by 46

38 more

2023Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoningcited by 45
2021Neural Point Process for Learning Spatiotemporal Event Dynamicscited by 42
2023Anticipatory Music Transformercited by 36
2022Exploring Generative Neural Temporal Point Processcited by 30
2023Prompt-augmented Temporal Point Process for Streaming Event Sequencecited by 24
2024A survey of dynamic graph neural networkscited by 24
2022Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processescited by 23
2023Add and Thin: Diffusion for Temporal Point Processescited by 23
2024Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Modelscited by 22
2021Long Horizon Forecasting With Temporal Point Processescited by 20
2022Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Mediacited by 20
2023Learning to Simulate Daily Activities via Modeling Dynamic Human Needscited by 20
2022A Graph Regularized Point Process Model For Event Propagation Sequencecited by 17
2023Meta Temporal Point Processescited by 17
2024Decomposable Transformer Point Processescited by 16
2024An Introduction to Deep Survival Analysis Models for Predicting Time-to-Event Outcomescited by 16
2022Mutual Distillation Learning Network for Trajectory-User Linkingcited by 15
2022Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequencescited by 14
2022Cardinality-Regularized Hawkes-Granger Modelcited by 14
2024Unlocking Point Processes through Point Set Diffusioncited by 14
2023Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Predictioncited by 13
2024HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?cited by 13
2021Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functionscited by 12
2021Region Invariant Normalizing Flows for Mobility Transfercited by 12
2022ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequencescited by 11
2024Deep Continuous-Time State-Space Models for Marked Event Sequencescited by 11
2021Neural Spectral Marked Point Processescited by 10
2021An Empirical Study: Extensive Deep Temporal Point Processcited by 10
2023Transformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysiscited by 10
2023Interacting Diffusion Processes for Event Sequence Forecastingcited by 10
2023A Systematic Review for Transformer-based Long-term Series Forecastingcited by 10
2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Maskcited by 10
2023Memory Efficient Neural Processes via Constant Memory Attention Blockcited by 9
2024Latent Logic Tree Extraction for Event Sequence Explanation from LLMscited by 9
2024TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Modelscited by 9
2022Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendationcited by 8
2022Spatio-temporal point processes with deep non-stationary kernelscited by 8
2023Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processescited by 8

50 most cited of 235 All 235 (JSON)