Neural Spatiotemporal Point Processes: Trends and Challenges
Abstract
Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibits intricate dependencies and heterogeneous dynamics. By incorporating modern deep learning techniques, STPPs can model these complexities more effectively than traditional approaches. Consequently, the fusion of neural methods with STPPs has become an active and rapidly evolving research area. In this review, we categorize existing approaches, unify key design choices, and explain the challenges of working with this data modality. We further highlight emerging trends and diverse application domains. Finally, we identify open challenges and gaps in the literature.
Cite
Text
Mukherjee et al. "Neural Spatiotemporal Point Processes: Trends and Challenges." Transactions on Machine Learning Research, 2025.Markdown
[Mukherjee et al. "Neural Spatiotemporal Point Processes: Trends and Challenges." Transactions on Machine Learning Research, 2025.](https://mlanthology.org/tmlr/2025/mukherjee2025tmlr-neural/)BibTeX
@article{mukherjee2025tmlr-neural,
title = {{Neural Spatiotemporal Point Processes: Trends and Challenges}},
author = {Mukherjee, Sumantrak and Elhamdi, Mouad and Mohler, George and Selby, David Antony and Xie, Yao and Vollmer, Sebastian Josef and Großmann, Gerrit},
journal = {Transactions on Machine Learning Research},
year = {2025},
url = {https://mlanthology.org/tmlr/2025/mukherjee2025tmlr-neural/}
}