Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting
Not on the map. Why?
Abstract (arXiv)
Accurate traffic state prediction is the foundation of transportation control and guidance. It is very challenging due to the complex spatiotemporal dependencies in traffic data. Existing works cannot perform well for multi-step traffic prediction that involves long future time period. The spatiotemporal information dilution becomes serve when the time gap between input step and predicted step is large, especially when traffic data is not sufficient or noisy. To address this issue, we propose a multi-spatial graph convolution based Seq2Seq model. Our main novelties are three aspects: (1) We enrich the spatiotemporal information of model inputs by fusing multi-view features (time, location and traffic states) (2) We build multiple kinds of spatial correlations based on both prior knowledge and data-driven knowledge to improve model performance especially in insufficient or noisy data cases. (3) A spatiotemporal attention mechanism based on reachability knowledge is novelly designed to produce high-level features fed into decoder of Seq2Seq directly to ease information dilution. Our model is evaluated on two real world traffic datasets and achieves better performance than other competitors.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 58 references that are in the map. First posted on arXiv 4 Jul 2021.
Builds on
27 of 58 references.
References · 27
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
- 2014DeepWalk: Online Learning of Social Representationscited by 1,547
- 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
15 more
- 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
- 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
- 2014Recurrent Models of Visual Attentioncited by 349
- 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 333
- 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 165
- 2018Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecastingcited by 146
- 2017DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understandingcited by 71
- 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
- 2019STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecastingcited by 60
- 2019Predicting Path Failure In Time-Evolving Graphscited by 54
- 2019Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networkscited by 40
- 2020How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Surveycited by 38
- 2019ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modelingcited by 19
- 20193D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecastingcited by 12
- 2019Revisiting Flow Information for Traffic Predictioncited by 3
Built on by
Not cited yet.