# The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process

arXiv: https://arxiv.org/abs/1612.09328 · HTML: https://mlsanity.com/paper/1612.09328/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2016.

## Built on by (most cited first, 13 of 13)

- [A Graph Regularized Point Process Model For Event Propagation Sequence](https://mlsanity.com/paper/2211.11758/) (2022)
- [EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning](https://mlsanity.com/paper/2303.12341/) (2023)
- [Extracting Attentive Social Temporal Excitation for Sequential Recommendation](https://mlsanity.com/paper/2109.13539/) (2021)
- [Bayesian Neural Hawkes Process for Event Uncertainty Prediction](https://mlsanity.com/paper/2112.14474/) (2021)
- [Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey](https://mlsanity.com/paper/2308.04947/) (2023)
- [Meta-Learning for Neural Network-based Temporal Point Processes](https://mlsanity.com/paper/2401.15846/) (2024)
- [Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism](https://mlsanity.com/paper/2106.01678/) (2021)
- [Semi-supervised Learning for Marked Temporal Point Processes](https://mlsanity.com/paper/2107.07729/) (2021)
- [Who Should I Engage with At What Time? A Missing Event Aware Temporal Graph Neural Network](https://mlsanity.com/paper/2301.08399/) (2023)
- [Deep-Learning vs Regression: Prediction of Tourism Flow with Limited Data](https://mlsanity.com/paper/2206.13274/) (2022)
- [Improving the Transferability of Time Series Forecasting with Decomposition Adaptation](https://mlsanity.com/paper/2307.00066/) (2023)
- [Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference](https://mlsanity.com/paper/2309.02868/) (2023)
- [Uncovering Social Network Activity Using Joint User and Topic Interaction](https://mlsanity.com/paper/2506.12842/) (2025)

## Abstract (arXiv)

Many events occur in the world. Some event types are stochastically excited or inhibited---in the sense of having their probabilities elevated or decreased---by patterns in the sequence of previous events. Discovering such patterns can help us predict which type of event will happen next and when. We model streams of discrete events in continuous time, by constructing a neurally self-modulating multivariate point process in which the intensities of multiple event types evolve according to a novel continuous-time LSTM. This generative model allows past events to influence the future in complex and realistic ways, by conditioning future event intensities on the hidden state of a recurrent neural network that has consumed the stream of past events. Our model has desirable qualitative properties. It achieves competitive likelihood and predictive accuracy on real and synthetic datasets, including under missing-data conditions.