Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes
This work addresses modeling complex event data with covariates for applications like epidemiology or urban planning, but it is incremental as it builds on existing deep mixture point processes.
The authors tackled the challenge of training a deep spatio-temporal point process model with multimodal covariates by proposing DKMPP, which uses a deep kernel for improved expressiveness and an integration-free score matching method for efficient training, resulting in performance gains over baseline models.
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.