Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction

• URL: http://arxiv.org/abs/2406.16992v1
• Date: Mon, 24 Jun 2024 07:32:58 GMT
• Title: Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction
• Authors: Yicheng Zhou, Pengfei Wang, Hao Dong, Denghui Zhang, Dingqi Yang, Yanjie Fu, Pengyang Wang,
• Abstract summary: We propose a generic model for enabling the current GNN-based methods to preserve topology-free patterns. Specifically, we first develop a Dual Cross-Scale Transformer (DCST) architecture, including a Spatial Transformer and a Temporal Transformer, to preserve the cross-scale topology-free patterns. We then propose a distillation-style learning framework, in which the existing GNN-based methods are considered as the teacher model, and the proposed DCST architecture is considered as the student model.
• Score: 29.096421050684516
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Urban traffic speed prediction aims to estimate the future traffic speed for improving urban transportation services. Enormous efforts have been made to exploit Graph Neural Networks (GNNs) for modeling spatial correlations and temporal dependencies of traffic speed evolving patterns, regularized by graph topology.While achieving promising results, current traffic speed prediction methods still suffer from ignoring topology-free patterns, which cannot be captured by GNNs. To tackle this challenge, we propose a generic model for enabling the current GNN-based methods to preserve topology-free patterns. Specifically, we first develop a Dual Cross-Scale Transformer (DCST) architecture, including a Spatial Transformer and a Temporal Transformer, to preserve the cross-scale topology-free patterns and associated dynamics, respectively. Then, to further integrate both topology-regularized/-free patterns, we propose a distillation-style learning framework, in which the existing GNN-based methods are considered as the teacher model, and the proposed DCST architecture is considered as the student model. The teacher model would inject the learned topology-regularized patterns into the student model for integrating topology-free patterns. The extensive experimental results demonstrated the effectiveness of our methods.

Related papers

• Improving Traffic Flow Predictions with SGCN-LSTM: A Hybrid Model for Spatial and Temporal Dependencies [55.2480439325792]
  This paper introduces the Signal-Enhanced Graph Convolutional Network Long Short Term Memory (SGCN-LSTM) model for predicting traffic speeds across road networks. Experiments on the PEMS-BAY road network traffic dataset demonstrate the SGCN-LSTM model's effectiveness.
  arXiv  Detail & Related papers  (2024-11-01T00:37:00Z)
• A Multi-Graph Convolutional Neural Network Model for Short-Term Prediction of Turning Movements at Signalized Intersections [0.6215404942415159]
  This study introduces a novel deep learning architecture, referred to as the multigraph convolution neural network (MGCNN) for turning movement prediction at intersections. The proposed architecture combines a multigraph structure, built to model temporal variations in traffic data, with a spectral convolution operation to support modeling the spatial variations in traffic data over the graphs. The model's ability to perform short-term predictions over 1, 2, 3, 4, and 5 minutes into the future was evaluated against four baseline state-of-the-art models.
  arXiv  Detail & Related papers  (2024-06-02T05:41:25Z)
• Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting [35.0288931087826]
  Traffic flow forecasting aims to predict future traffic conditions on the basis of networks and traffic conditions in the past. The problem is typically solved by modeling complex-temporal correlations in traffic data using far-temporal neural networks (GNNs) Existing methods follow the paradigm of message passing that aggregates neighborhood information linearly. In this paper, we propose a model named Dynamic Hyper Structure Learning (DyHSL) for traffic flow prediction.
  arXiv  Detail & Related papers  (2023-09-21T12:44:55Z)
• Dynamic Causal Graph Convolutional Network for Traffic Prediction [19.759695727682935]
  We propose an approach for predicting traffic that embeds time-varying dynamic network to capture finetemporal patterns of traffic data. We then use graph convolutional networks to generate traffic forecasts. Our experimental results on a real traffic dataset demonstrate the superior prediction performance of the proposed method.
  arXiv  Detail & Related papers  (2023-06-12T10:46:31Z)
• Graph-based Multi-ODE Neural Networks for Spatio-Temporal Traffic Forecasting [8.832864937330722]
  Long-range traffic forecasting remains a challenging task due to the intricate and extensive-temporal correlations observed in traffic networks. In this paper, we propose a architecture called Graph-based Multi-ODE Neural Networks (GRAM-ODE) which is designed with multiple connective ODE-GNN modules to learn better representations. Our extensive set of experiments conducted on six real-world datasets demonstrate the superior performance of GRAM-ODE compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-05-30T02:10:42Z)
• Attention-based Spatial-Temporal Graph Neural ODE for Traffic Prediction [3.4806267677524896]
  We propose attention-based graph neural ODE (AST) that explicitly learns the dynamics of the traffic system. Our model aggregates traffic patterns of different periods and has satisfactory performance on two real-world traffic data sets.
  arXiv  Detail & Related papers  (2023-05-01T00:58:48Z)
• PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction [78.05103666987655]
  spatial-temporal Graph Neural Network (GNN) models have emerged as one of the most promising methods to solve this problem. We propose a novel propagation delay-aware dynamic long-range transFormer, namely PDFormer, for accurate traffic flow prediction. Our method can not only achieve state-of-the-art performance but also exhibit competitive computational efficiency.
  arXiv  Detail & Related papers  (2023-01-19T08:42:40Z)
• Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs [77.33781731432163]
  We learn dynamic graph representation in hyperbolic space, for the first time, which aims to infer node representations. We present a novel Hyperbolic Variational Graph Network, referred to as HVGNN. In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach.
  arXiv  Detail & Related papers  (2021-04-06T01:44:15Z)
• Overcoming Catastrophic Forgetting in Graph Neural Networks [50.900153089330175]
  Catastrophic forgetting refers to the tendency that a neural network "forgets" the previous learned knowledge upon learning new tasks. We propose a novel scheme dedicated to overcoming this problem and hence strengthen continual learning in graph neural networks (GNNs) At the heart of our approach is a generic module, termed as topology-aware weight preserving(TWP)
  arXiv  Detail & Related papers  (2020-12-10T22:30:25Z)
• Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2020-10-06T01:20:27Z)
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting [88.5550074808201]
  We propose Geographic and Long term Temporal Graph Convolutional Recurrent Neural Network (GLT-GCRNN) for traffic forecasting. In this work, we propose a novel framework for traffic forecasting that learns the rich interactions between roads sharing similar geographic or longterm temporal patterns.
  arXiv  Detail & Related papers  (2020-04-23T03:50:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.