TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting
- 14 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (2) , 2003-2013
Abstract
This article aims to unify spatial dependency and temporal dependency in a non-Euclidean space while capturing the inner spatial–temporal dependencies for traffic data. For spatial–temporal attribute entities with topological structure, the space–time is consecutive and unified while each node’s current status is influenced by its neighbors’ past states over variant periods of each neighbor. Most spatial–temporal neural networks for traffic forecasting study spatial dependency and temporal correlation separately in processing, gravely impaired the spatial–temporal integrity, and ignore the fact that the neighbors’ temporal dependency period for a node can be delayed and dynamic. To model this actual condition, we propose TraverseNet, a novel spatial–temporal graph neural network, viewing space and time as an inseparable whole, to mine spatial–temporal graphs while exploiting the evolving spatial–temporal dependencies for each node via message traverse mechanisms. Experiments with ablation and parameter studies have validated the effectiveness of the proposed TraverseNet, and the detailed implementation can be found from https://github.com/nnzhan/TraverseNet.Keywords
All Related Versions
Funding Information
- Australian Research Council (ARC) Future Fellowship (FT210100097)
This publication has 24 references indexed in Scilit:
- Graph-Time Convolutional Neural Networks2021
- Graph Neural Networks with Convolutional ARMA FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks2020
- Traffic Flow Prediction via Spatial Temporal Graph Neural Network2020
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020
- Graph Representation Learning via Hard and Channel-Wise Attention Networks2019
- Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning2019
- Structured Sequence Modeling with Graph Convolutional Recurrent Networks2018
- CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral FiltersIEEE Transactions on Signal Processing, 2018
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs2017