Neural Spatiotemporal Point Processes: Trends and Challenges

TMLR Paper5324 Authors

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 categorise 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.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Vincent_Fortuin1

Submission Number: 5324