Traffic Flow Prediction via Spatial Temporal Graph Neural Network
Прогнозирование транспортных потоков с помощью пространственно-временной графовой нейронной сети
2020-04-20
SCID: 54.1/bfzf236a
Discuss with AI
positional attention mechanismspatial-temporal dependenciesspatiotemporal graph neural networktraffic datasetstraffic flow prediction
Figures from the paper
Abstract (AI)
Traffic flow analysis, prediction and management are keystones for building smart cities in the new era. With the help of deep neural networks and big traffic data, we can better understand the latent patterns hidden in the complex transportation networks. The dynamic of the traffic flow on one road not only depends on the sequential patterns in the temporal dimension but also relies on other roads in the spatial dimension. Although there are existing works on predicting the future traffic flow, the majority of them have certain limitations on modeling spatial and temporal dependencies. In this paper, we propose a novel spatial temporal graph neural network for traffic flow prediction, which can comprehensively capture spatial and temporal patterns. In particular, the framework offers a learnable positional attention mechanism to effectively aggregate information from adjacent roads. Meanwhile, it provides a sequential component to model the traffic flow dynamics which can exploit both local and global temporal dependencies. Experimental results on various real traffic datasets demonstrate the effectiveness of the proposed framework.
Key Findings
1
A learnable positional attention mechanism aggregates information from adjacent roads to capture spatial traffic relationships.
2
A sequential component models traffic dynamics by exploiting both local and global temporal dependencies.
3
Experiments on multiple real-world traffic datasets demonstrate the framework’s effectiveness for traffic flow prediction.
4
The paper introduces a spatial-temporal graph neural network designed to jointly model spatial and temporal dependencies in traffic flow.
Research Object
traffic flow on interconnected road networks
Research Subject
spatiotemporal dependencies and prediction dynamics of traffic flow, including spatial interactions among adjacent roads and local/global temporal patterns
Publication Details
Publication Date
2020-04-20
Journal
Publisher
ISSN
Cited by
676
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
Deep Residual Learning for Image Recognition2016
Semi-Supervised Classification with Graph Convolutional Networks2016
Sequence to Sequence Learning with Neural Networks2014
A Comprehensive Survey on Graph Neural Networks2020
The Graph Neural Network Model2008
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation2014
Knowledge Graph Embedding: A Survey of Approaches and Applications2017
Cited by4
Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey2023
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection2024
Decoupled dynamic spatial-temporal graph neural network for traffic forecasting2022
A Survey on Graph Representation Learning Methods2023