Neural Spatiotemporal Point Processes: Trends and Challenges
This is an incremental review that synthesizes existing research for practitioners and researchers in machine learning and related domains.
The paper reviews the integration of neural methods with spatiotemporal point processes to model complex event data, categorizing approaches and identifying trends and challenges in the field.
Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibit 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.