Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Haiyang, Zhu, Chunjiang, Zhang, Detian
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2401.04135
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916085134000128
author Liu, Haiyang
Zhu, Chunjiang
Zhang, Detian
author_facet Liu, Haiyang
Zhu, Chunjiang
Zhang, Detian
contents Traffic flow prediction plays a crucial role in alleviating traffic congestion and enhancing transport efficiency. While combining graph convolution networks with recurrent neural networks for spatial-temporal modeling is a common strategy in this realm, the restricted structure of recurrent neural networks limits their ability to capture global information. For spatial modeling, many prior studies learn a graph structure that is assumed to be fixed and uniform at all time steps, which may not be true. This paper introduces a novel traffic prediction framework, Global-Aware Enhanced Spatial-Temporal Graph Recurrent Network (GA-STGRN), comprising two core components: a spatial-temporal graph recurrent neural network and a global awareness layer. Within this framework, three innovative prediction models are formulated. A sequence-aware graph neural network is proposed and integrated into the Gated Recurrent Unit (GRU) to learn non-fixed graphs at different time steps and capture local temporal relationships. To enhance the model's global perception, three distinct global spatial-temporal transformer-like architectures (GST^2) are devised for the global awareness layer. We conduct extensive experiments on four real traffic datasets and the results demonstrate the superiority of our framework and the three concrete models.
format Preprint
id arxiv_https___arxiv_org_abs_2401_04135
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Global-Aware Enhanced Spatial-Temporal Graph Recurrent Networks: A New Framework For Traffic Flow Prediction
Liu, Haiyang
Zhu, Chunjiang
Zhang, Detian
Machine Learning
Artificial Intelligence
Traffic flow prediction plays a crucial role in alleviating traffic congestion and enhancing transport efficiency. While combining graph convolution networks with recurrent neural networks for spatial-temporal modeling is a common strategy in this realm, the restricted structure of recurrent neural networks limits their ability to capture global information. For spatial modeling, many prior studies learn a graph structure that is assumed to be fixed and uniform at all time steps, which may not be true. This paper introduces a novel traffic prediction framework, Global-Aware Enhanced Spatial-Temporal Graph Recurrent Network (GA-STGRN), comprising two core components: a spatial-temporal graph recurrent neural network and a global awareness layer. Within this framework, three innovative prediction models are formulated. A sequence-aware graph neural network is proposed and integrated into the Gated Recurrent Unit (GRU) to learn non-fixed graphs at different time steps and capture local temporal relationships. To enhance the model's global perception, three distinct global spatial-temporal transformer-like architectures (GST^2) are devised for the global awareness layer. We conduct extensive experiments on four real traffic datasets and the results demonstrate the superiority of our framework and the three concrete models.
title Global-Aware Enhanced Spatial-Temporal Graph Recurrent Networks: A New Framework For Traffic Flow Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.04135