Spatiotemporal Graph Neural Network

Spatiotemporal Graph Neural Networks (ST-GNNs) are a class of deep learning models designed to analyze data with complex spatial and temporal dependencies, aiming to improve prediction accuracy and uncertainty quantification in various domains. Current research focuses on enhancing the robustness and scalability of ST-GNNs, particularly addressing challenges like handling sparse data, adapting to out-of-distribution scenarios, and incorporating multimodal information through architectures such as Mixture of Experts and multi-relational graph networks. These advancements have significant implications for applications ranging from traffic forecasting and power outage prediction to environmental monitoring and disaster response, enabling more accurate and reliable predictions in dynamic systems.

Papers

November 18, 2024

Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting
Hongjun Wang, Jiyuan Chen, Lingyu Zhang, Renhe Jiang, Xuan Song
Adaptive Importance Traffic Prediction Traffic Forecasting Traffic Pattern Spatiotemporal Modeling Spatiotemporal Graph Neural Network

October 17, 2024

Interpreting Temporal Graph Neural Networks with Koopman Theory
Michele Guerra, Simone Scardapane, Filippo Maria Bianchi
High Explainability Dynamical System Temporal Graph Koopman Operator Temporal Graph Neural Network Temporal Pattern Spatiotemporal Graph Neural Network

October 1, 2024

Robust Traffic Forecasting against Spatial Shift over Years
Hongjun Wang, Jiyuan Chen, Tong Pan, Zheng Dong, Lingyu Zhang, Renhe Jiang, Xuan Song
Traffic Forecasting Last Decade Temporal Shift Spatiotemporal Modeling Spatiotemporal Graph Neural Network

September 14, 2024

Multimodal Power Outage Prediction for Rapid Disaster Response and Resource Allocation
Alejandro Aparcedo, Christian Lopez, Abhinav Kotta, Mengjie Li
Resource Allocation Spatiotemporal Representation Disaster Response Spatiotemporal Graph Neural Network Power Outage

September 13, 2024

SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks
Dingyi Zhuang, Yuheng Bu, Guang Wang, Shenhao Wang, Jinhua Zhao
Graph Neural Network Uncertainty Calibration Spatiotemporal Prediction Spatiotemporal Datasets Spatiotemporal Graph Neural Network Spatiotemporal Deep Learning

May 6, 2024

Denoising of Geodetic Time Series Using Spatiotemporal Graph Neural Networks: Application to Slow Slip Event Extraction
Giuseppe Costantino, Sophie Giffard-Roisin, Mauro Dalla Mura, Anne Socquet
Application Proficiency Time Series Denoising Process Global Navigation Satellite System Seismic Data Graph Signal Denoising Large Displacement Spatiotemporal Graph Neural Network Slow Slip

April 8, 2024

Back to the Future: GNN-based NO$_2$ Forecasting via Future Covariates
Antonio Giganti, Sara Mandelli, Paolo Bestagini, Umberto Giuriato, Alessandro D'Ausilio, Marco Marcon, Stefano Tubaro
Future Reasoning Spatiotemporal Representation Prediction Horizon Air Quality Forecasting Time Varying Covariates Forecasting Analysis Spatiotemporal Graph Neural Network

September 10, 2023

Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction
Xiaowei Gao, Xinke Jiang, Dingyi Zhuang, Huanfa Chen, Shenhao Wang, Stephen Law, James Haworth
Traffic Accident Traffic Accident Prediction Spatiotemporal Graph Neural Network

May 30, 2023

Graph Neural Network for spatiotemporal data: methods and applications
Yun Li, Dazhou Yu, Zhenke Liu, Minxing Zhang, Xiaoyun Gong, Liang Zhao
Graph Neural Network Financial Application NCD Method Spatio tempOral SpatioTemporal Data Spatiotemporal Graph Neural Network

January 25, 2023

Spatio-Temporal Graph Neural Networks: A Survey
Zahraa Al Sahili, Mariette Awad
Graph Neural Network Timely Survey Deep Learning Algorithm Temporal Graph Neural Network Spatiotemporal Graph Neural Network

September 14, 2022

Scalable Spatiotemporal Graph Neural Networks
Andrea Cini, Ivan Marisca, Filippo Maria Bianchi, Cesare Alippi
Multi Scale Spatiotemporal Feature Neural Forecasting Spatiotemporal Graph Neural Network Time sEries

April 4, 2022

Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting
Tanwi Mallick, Prasanna Balaprakash, Jane Macfarlane
Uncertainty Quantification Traffic Forecasting Convolutional Recurrent Short Term Traffic Spatiotemporal Graph Neural Network Diffusion Convolutional Recurrent Neural Network

December 15, 2021

Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach
Yuebing Liang, Guan Huang, Zhan Zhao
Multi Task Time Series Forecasting Joint predictioN Demand Forecasting Multimodal System Spatiotemporal Graph Spatiotemporal Correlation Spatiotemporal Graph Neural Network