Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes

TL;DR

This paper introduces DKMPP, a novel deep spatio-temporal point process model that effectively incorporates multimodal covariate data using an integration-free score matching approach, leading to improved modeling of complex event relationships.

Contribution

The paper presents DKMPP, a flexible deep kernel-based model for spatio-temporal point processes, and introduces an integration-free training method using score matching for enhanced efficiency.

Findings

DKMPP outperforms baseline models in experiments.

Score matching improves training efficiency.

Incorporating covariates enhances model expressiveness.

Abstract

In this study, we propose a novel deep spatio-temporal point process model, Deep Kernel Mixture Point Processes (DKMPP), that incorporates multimodal covariate information. DKMPP is an enhanced version of Deep Mixture Point Processes (DMPP), which uses a more flexible deep kernel to model complex relationships between events and covariate data, improving the model's expressiveness. To address the intractable training procedure of DKMPP due to the non-integrable deep kernel, we utilize an integration-free method based on score matching, and further improve efficiency by adopting a scalable denoising score matching method. Our experiments demonstrate that DKMPP and its corresponding score-based estimators outperform baseline models, showcasing the advantages of incorporating covariate information, utilizing a deep kernel, and employing score-based estimators.