# Learning Structure-enhanced Temporal Point Processes with Gromov-Wasserstein Regularization

arXiv: https://arxiv.org/abs/2503.23002 · HTML: https://mlsanity.com/paper/2503.23002/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 29 Mar 2025.

## Builds on (most cited first, 12 of 12)

- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching](https://mlsanity.com/paper/1905.07645/) (2019)
- [SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity](https://mlsanity.com/paper/1506.02594/) (2015)
- [HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences](https://mlsanity.com/paper/2210.01753/) (2022)
- [Generalized Spectral Clustering via Gromov-Wasserstein Learning](https://mlsanity.com/paper/2006.04163/) (2020)
- [COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution](https://mlsanity.com/paper/1507.02293/) (2015)
- [Discovering Latent Network Structure in Point Process Data](https://mlsanity.com/paper/1402.0914/) (2014)
- [Interval-censored Transformer Hawkes: Detecting Information Operations using the Reaction of Social Systems](https://mlsanity.com/paper/2211.14114/) (2022)
- [Stimuli-Sensitive Hawkes Processes for Personalized Student Procrastination Modeling](https://mlsanity.com/paper/2102.00089/) (2021)
- [The Block Point Process Model for Continuous-Time Event-Based Dynamic Networks](https://mlsanity.com/paper/1711.10967/) (2017)
- [Modeling and Predicting Popularity Dynamics of Microblogs using Self-Excited Hawkes Processes](https://mlsanity.com/paper/1503.02754/) (2015)
- [THAP: A Matlab Toolkit for Learning with Hawkes Processes](https://mlsanity.com/paper/1708.09252/) (2017)

## Abstract (arXiv)

Real-world event sequences are often generated by different temporal point processes (TPPs) and thus have clustering structures. Nonetheless, in the modeling and prediction of event sequences, most existing TPPs ignore the inherent clustering structures of the event sequences, leading to the models with unsatisfactory interpretability. In this study, we learn structure-enhanced TPPs with the help of Gromov-Wasserstein (GW) regularization, which imposes clustering structures on the sequence-level embeddings of the TPPs in the maximum likelihood estimation framework.In the training phase, the proposed method leverages a nonparametric TPP kernel to regularize the similarity matrix derived based on the sequence embeddings. In large-scale applications, we sample the kernel matrix and implement the regularization as a Gromov-Wasserstein (GW) discrepancy term, which achieves a trade-off between regularity and computational efficiency.The TPPs learned through this method result in clustered sequence embeddings and demonstrate competitive predictive and clustering performance, significantly improving the model interpretability without compromising prediction accuracy.