ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations

TL;DR

ProGen introduces a continuous diffusion-based probabilistic framework for spatiotemporal forecasting using stochastic differential equations, effectively capturing complex dependencies and uncertainty in traffic data.

Contribution

It presents a novel continuous generative model combining SDEs, denoising score models, and graph neural networks for improved spatiotemporal forecasting.

Findings

Outperforms state-of-the-art models on traffic datasets

Effectively models uncertainty and complex dependencies

Demonstrates robustness across multiple benchmarks

Abstract

Accurate forecasting of spatiotemporal data remains challenging due to complex spatial dependencies and temporal dynamics. The inherent uncertainty and variability in such data often render deterministic models insufficient, prompting a shift towards probabilistic approaches, where diffusion-based generative models have emerged as effective solutions. In this paper, we present ProGen, a novel framework for probabilistic spatiotemporal time series forecasting that leverages Stochastic Differential Equations (SDEs) and diffusion-based generative modeling techniques in the continuous domain. By integrating a novel denoising score model, graph neural networks, and a tailored SDE, ProGen provides a robust solution that effectively captures spatiotemporal dependencies while managing uncertainty. Our extensive experiments on four benchmark traffic datasets demonstrate that ProGen outperforms state-of-the-art deterministic and probabilistic models. This work contributes a continuous, diffusion-based generative approach to spatiotemporal forecasting, paving the way for future research in probabilistic modeling and stochastic processes.