DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models

01/31/2023
by   Haomin Wen, et al.
0

Spatio-temporal graph neural networks (STGNN) have emerged as the dominant model for spatio-temporal graph (STG) forecasting. Despite their success, they fail to model intrinsic uncertainties within STG data, which cripples their practicality in downstream tasks for decision-making. To this end, this paper focuses on probabilistic STG forecasting, which is challenging due to the difficulty in modeling uncertainties and complex ST dependencies. In this study, we present the first attempt to generalize the popular denoising diffusion probabilistic models to STGs, leading to a novel non-autoregressive framework called DiffSTG, along with the first denoising network UGnet for STG in the framework. Our approach combines the spatio-temporal learning capabilities of STGNNs with the uncertainty measurements of diffusion models. Extensive experiments validate that DiffSTG reduces the Continuous Ranked Probability Score (CRPS) by 4 over existing methods on three real-world datasets.

READ FULL TEXT

page 5

page 7

page 14

page 15

research
03/31/2020

A Spatio-Temporal Spot-Forecasting Framework for Urban Traffic Prediction

Spatio-temporal forecasting is an open research field whose interest is ...
research
11/21/2022

Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks

Forecasting future states of sensors is key to solving tasks like weathe...
research
05/30/2023

Graph Neural Processes for Spatio-Temporal Extrapolation

We study the task of spatio-temporal extrapolation that generates data a...
research
12/07/2018

Back to square one: probabilistic trajectory forecasting without bells and whistles

We introduce a spatio-temporal convolutional neural network model for tr...
research
05/16/2023

Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecasting

Graph neural networks (GNNs), especially dynamic GNNs, have become a res...
research
11/27/2020

Efficient Information Diffusion in Time-Varying Graphs through Deep Reinforcement Learning

Network seeding for efficient information diffusion over time-varying gr...
research
01/11/2021

Bayesian Surrogate Analysis and Uncertainty Propagation with Explicit Surrogate Uncertainties and Implicit Spatio-temporal Correlations

We introduce Bayesian Probability Theory to investigate uncertainty prop...

Please sign up or login with your details

Forgot password? Click here to reset