Neural Spatiotemporal Point Processes: Trends and Challenges

TL;DR

This paper reviews the integration of neural networks with spatiotemporal point processes, highlighting recent trends, challenges, and diverse applications in modeling complex event data in space and time.

Contribution

It categorizes existing neural STPP approaches, unifies design choices, and discusses current challenges and emerging trends in this rapidly evolving field.

Findings

Neural methods improve modeling of complex dependencies in spatiotemporal data.

The review identifies key challenges and open problems in neural STPP research.

Emerging applications span various domains, demonstrating the versatility of neural STPPs.

Abstract

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.