Dynamic Localisation of Spatial-Temporal Graph Neural Network
Not on the map. Why?
Abstract (arXiv)
Spatial-temporal data, fundamental to many intelligent applications, reveals dependencies indicating causal links between present measurements at specific locations and historical data at the same or other locations. Within this context, adaptive spatial-temporal graph neural networks (ASTGNNs) have emerged as valuable tools for modelling these dependencies, especially through a data-driven approach rather than pre-defined spatial graphs. While this approach offers higher accuracy, it presents increased computational demands. Addressing this challenge, this paper delves into the concept of localisation within ASTGNNs, introducing an innovative perspective that spatial dependencies should be dynamically evolving over time. We introduce textitDynAGS, a localised ASTGNN framework aimed at maximising efficiency and accuracy in distributed deployment. This framework integrates dynamic localisation, time-evolving spatial graphs, and personalised localisation, all orchestrated around the Dynamic Graph Generator, a light-weighted central module leveraging cross attention. The central module can integrate historical information in a node-independent manner to enhance the feature representation of nodes at the current moment. This improved feature representation is then used to generate a dynamic sparse graph without the need for costly data exchanges, and it supports personalised localisation. Performance assessments across two core ASTGNN architectures and nine real-world datasets from various applications reveal that textitDynAGS outshines current benchmarks, underscoring that the dynamic modelling of spatial dependencies can drastically improve model expressibility, flexibility, and system efficiency, especially in distributed settings.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 8 Jan 2025.
Builds on
20 of 34 references.
References · 20
- 2017Graph Attention Networkscited by 8,854
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
- 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
- 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
- 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
- 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
- 2018Deep Multi-View Spatial-Temporal Network for Taxi Demand Predictioncited by 162
- 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 156
- 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
- 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
8 more
- 2023LargeST: A Benchmark Dataset for Large-Scale Traffic Forecastingcited by 116
- 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
- 2021Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecastingcited by 67
- 2019STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecastingcited by 59
- 2021Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Ticketscited by 27
- 2023Localised Adaptive Spatial-Temporal Graph Neural Networkcited by 14
- 2019Dissecting Ethereum Blockchain Analytics: What We Learn from Topology and Geometry of Ethereum Graphcited by 11
- 2022Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworkscited by 8
Built on by
Citing papers per year: 2026: 2.
2 papers.