Spatiotemporal GNNs

GNN: Graph Neural Network

Overview

Spatiotemporal graph neural networks represent entities such as traffic sensors, body joints, or mesh elements as nodes, and use their connections to model how information changes over time. Common approaches combine graph convolutions or attention with recurrent networks, temporal convolutions, Transformers, or continuous-time models; some also learn changing graph structure or incorporate physical constraints. They are used for traffic forecasting, human-motion prediction, environmental modeling, and simulation, with evaluation ranging from traffic datasets such as METR-LA and PEMS to motion benchmarks such as Human3.6M. A central challenge is balancing accuracy and long-horizon stability with computational cost, while ensuring models generalize across regions, changing conditions, and irregular or sparse observations.

Latest papers

CardsList

163 papers17 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. ST-GAT: A Leakage-Free Spatio-Temporal Graph Attention Framework for Robust Network Intrusion Detection

    Nov 14, 2026Nikhil Parkar, Sanskar Pandey, Siddhi Prajapati +2Network Intrusion DetectionSpatiotemporal GNNs

  2. Physical-Risk-Aware Decentralized Agents for Constrained Vehicle Communications

    Nov 12, 2026Haoran Peng, William Weijia Zheng, Hang Liu +1V2X CommunicationRisk-Aware Control

  3. DySR-GNN: Dynamic Sensor-Relationship Graph Neural Network for Root Cause Analysis in Automotive HiL Multivariate Time Series

    Nov 12, 2026Hamza Ouarrad, Mohammad Abboush, Andreas RauschRoot Cause AnalysisFault Diagnosis

  4. Beyond Sunny Skies: Using Large Language Models to Predict Urban Traffic in Adverse Weather

    Nov 9, 2026Zhu Xiao, Kuan Feng, Tong Li +4Traffic ForecastingContext-Aware Time Series Forecasting

  5. SIMBAD: Spatio-Temporal Traffic Forecasting Robust to Aperiodicity

    Nov 6, 2026Daniel Y. Lee, Seungwon Shin, Seunghoon Han +2Spatiotemporal ForecastingTraffic Forecasting

  6. Coupled Scene Graph Anticipation: When With-Constraint Recall Hides Structural Inconsistency

    Nov 4, 2026Zeno Nongmaithem, Anushttha Srivastava, Anshit Sinha +4Video SGGScene Graph Generation

  7. GraphSeal: Graph-Augmented Speech Deepfake Detection via Temporal-Spectral Artifact Propagation

    Nov 4, 2026Lee Seung-woo, Bowen Qi, Kim Min-jun +1Audio Deepfake DetectionASVspoof

  8. ST-GFM: Spectral-Temporal Graph Forecasting with Measured Perturbation Bounds and Masked Spectral Reconstruction

    Nov 2, 2026Aashish Bohra, Vivek VijaySpatiotemporal ForecastingSpatiotemporal GNNs

  9. Control Foundation Models across Changing Block Diagrams: Generalizing Time-Series Prediction to Dynamic Graphs

    Nov 2, 2026Yuji Okamoto, Kenta Hoshino, Masaki InoueTime-Series Foundation ModelsNeural Network Control

  10. TGTV: An Interpretable Framework for UAV Fault Detection and Traceability via Spatiotemporal Graph Learning and Large Language Models

    Oct 28, 2026Zixuan Wang, Changbo Shi, Ji LiuFault DetectionFault Diagnosis

  11. GraphCast-Mamba: Learning Non-Markovian Corrections for Weather Forecasting

    Oct 20, 2026Ilya Vilkoviskiy, Liang-Hong Mo, Suozhi Huang +1Weather ForecastingTime Series Forecasting

  12. Cross-Visibility-Gap Identity Persistence for 4D Scene Graphs

    Oct 20, 2026Jiahui Hu, Li Gao, Yu Liu +14D Scene UnderstandingMulti-Object Tracking

  13. STC-MGNet: Spatial-Temporal-Channel Attention-Enhanced Multimodal Graph Network for Pedestrian Intention Prediction

    Oct 16, 2026Yuanzhe Li, Meng WangPedestrian Intention PredictionSpatiotemporal GNNs

  14. Towards a GraphNARX model for structural dynamics

    Oct 16, 2026George Tsialiamanis, Keith WordenNonlinear System IdentificationTime Series Modeling

  15. Choosing models for network-wide freeway speed estimation and forecasting from sparse fixed sensors

    Oct 15, 2026Ran Tu, Zihao Li, Arash MirzaeiTraffic ForecastingTraffic Flow Estimation

  16. Learning to Forecast on Multiple Spatiotemporal Hierarchies

    Oct 15, 2026Valentina Moretti, Cesare Alippi, Andrea CiniTime Series ForecastingSpatiotemporal Forecasting

  17. Learning and Forecasting Multiscale Spatiotemporal Epidemic Dynamics with Lagrangian-Eulerian Graph Neural ODEs

    Oct 15, 2026Jinyi Duan, Qian Li, Biao TangEpidemic ForecastingSpatial Epidemic Modeling

  18. FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks

    Oct 13, 2026Aiyshwariya Paulvannan Kanmani, Miguel Esparza, Ali MostafaviWildfire ForecastingSpatiotemporal GNNs

  19. From Rainfall to Road-Network Functionality: Transferable Graph Forecasting for Flood-Disrupted Transportation Networks

    Oct 10, 2026Junyan Wang, Naiyu WangSpatiotemporal ForecastingSpatiotemporal GNNs

  20. Robot-WATCHDOG : failure detection through object-centric graph representation

    Oct 9, 2026Quentin Rolland, Fabrice Mayran de Chamisso, Jean-Baptiste MouretRobot Failure DetectionRobotic Anomaly Detection

  21. LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction

    Oct 2, 2026Xuxilu Zhang, Francesc SorigueraSpatiotemporal ForecastingTime Series Forecasting

  22. Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphs

    Oct 1, 2026Haoyang Jiang, Zhengui Wang, Shenghan Gao +3Spatiotemporal ForecastingPhysics-Informed GNNs

  23. FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model

    Sep 28, 2026Shucheng Liu, Changchun Shi, Kai Zhang +1Neural Surrogate ModelingFunctional Connectivity

  24. Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction

    Sep 26, 2026Yixuan Wang, Brandon C. Fallin, Warren E. DixonHuman Motion PredictionFlow Matching