# Self-Attentive Hawkes Processes

arXiv: https://arxiv.org/abs/1907.07561 · HTML: https://mlsanity.com/paper/1907.07561/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2019.

## Built on by (most cited first, 23 of 23)

- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [Neural Point Process for Learning Spatiotemporal Event Dynamics](https://mlsanity.com/paper/2112.06351/) (2021)
- [A Graph Regularized Point Process Model For Event Propagation Sequence](https://mlsanity.com/paper/2211.11758/) (2022)
- [On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Data](https://mlsanity.com/paper/2306.17066/) (2023)
- [Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions](https://mlsanity.com/paper/2107.03354/) (2021)
- [Region Invariant Normalizing Flows for Mobility Transfer](https://mlsanity.com/paper/2109.05738/) (2021)
- [ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences](https://mlsanity.com/paper/2206.05291/) (2022)
- [Neural Spectral Marked Point Processes](https://mlsanity.com/paper/2106.10773/) (2021)
- [Distribution-Free Conformal Joint Prediction Regions for Neural Marked Temporal Point Processes](https://mlsanity.com/paper/2401.04612/) (2024)
- [Modeling Continuous Time Sequences with Intermittent Observations using Marked Temporal Point Processes](https://mlsanity.com/paper/2206.12414/) (2022)
- [Online Learning for Mixture of Multivariate Hawkes Processes](https://mlsanity.com/paper/2208.07961/) (2022)
- [Modeling Time-Series and Spatial Data for Recommendations and Other Applications](https://mlsanity.com/paper/2212.13259/) (2022)
- [Embeddings for Tabular Data: A Survey](https://mlsanity.com/paper/2302.11777/) (2023)
- [Deep Convolution for Irregularly Sampled Temporal Point Clouds](https://mlsanity.com/paper/2105.00137/) (2021)
- [Retrieving Continuous Time Event Sequences using Neural Temporal Point Processes with Learnable Hashing](https://mlsanity.com/paper/2307.09613/) (2023)
- [Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows](https://mlsanity.com/paper/2307.10305/) (2023)
- [A Simple Baseline for Predicting Events with Auto-Regressive Tabular Transformers](https://mlsanity.com/paper/2410.10648/) (2024)
- [Fine-Grained ε-Margin Closed-Form Stabilization of Parametric Hawkes Processes](https://mlsanity.com/paper/2105.03800/) (2021)
- [Challenges and opportunities in applying Neural Temporal Point Processes to large scale industry data](https://mlsanity.com/paper/2208.08623/) (2022)
- [Fast Learning of Multidimensional Hawkes Processes via Frank-Wolfe](https://mlsanity.com/paper/2212.06081/) (2022)
- [Preventing Conflicting Gradients in Neural Marked Temporal Point Processes](https://mlsanity.com/paper/2412.08590/) (2024)
- [Differentiable Adversarial Attacks for Marked Temporal Point Processes](https://mlsanity.com/paper/2501.10606/) (2025)
- [GAttNHP: Group Attention Neural Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs](https://mlsanity.com/paper/2607.14733/) (2026)

## Abstract (arXiv)

Asynchronous events on the continuous time domain, e.g., social media actions and stock transactions, occur frequently in the world. The ability to recognize occurrence patterns of event sequences is crucial to predict which typeof events will happen next and when. A de facto standard mathematical framework to do this is the Hawkes process. In order to enhance expressivity of multivariate Hawkes processes, conventional statistical methods and deep recurrent networks have been employed to modify its intensity function. The former is highly interpretable and requires small size of training data but relies on correct model design while the latter has less dependency on prior knowledge and is more powerful in capturing complicated patterns. We leverage pros and cons of these models and propose a self-attentive Hawkes process(SAHP). The proposed method adapts self-attention to fit the intensity function of Hawkes processes. This design has two benefits:(1) compared with conventional statistical methods, the SAHP is more powerful to identify complicated dependency relationships between temporal events; (2)compared with deep recurrent networks, the self-attention mechanism is able to capture longer historical information, and is more interpretable because the learnt attention weight tensor shows contributions of each historical event. Experiments on four real-world datasets demonstrate the effectiveness of the proposed method.