ST-GRAT: A Novel Spatio-temporal Graph Attention Networks for Accurately Forecasting Dynamically Changing Road Speed

Abstract

Predicting road traffic speed is a challenging task due to different types of roads, abrupt speed change and spatial dependencies between roads; it requires the modeling of dynamically changing spatial dependencies among roads and temporal patterns over long input sequences. This paper proposes a novel spatio-temporal graph attention (ST-GRAT) that effectively captures the spatio-temporal dynamics in road networks. The novel aspects of our approach mainly include spatial attention, temporal attention, and spatial sentinel vectors. The spatial attention takes the graph structure information (e.g., distance between roads) and dynamically adjusts spatial correlation based on road states. The temporal attention is responsible for capturing traffic speed changes, and the sentinel vectors allow the model to retrieve new features from spatially correlated nodes or preserve existing features. The experimental results show that ST-GRAT outperforms existing models, especially in difficult conditions where traffic speeds rapidly change (e.g., rush hours). We additionally provide a qualitative study to analyze when and where ST-GRAT tended to make accurate predictions during rush-hour times. CCS CONCEPTS • Information systems → Spatial-temporal systems; • Mathematics of computing → Time series analysis.

Spatial‐temporal attention wavenet: A deep learning framework for traffic prediction considering spatial‐temporal dependencies

“…To demonstrate the effectiveness of the proposed model, We compare STAWnet with the following models: HA: Historical average, which is a naive method that models the traffic flow as a periodic process and uses the weighted average of previous periods as the prediction. ARIMA: Auto‐Regressive Integrated Moving Average Model, which is a classical time series prediction model. FC‐LSTM: Recurrent neural network with fully connected LSTM hidden units [43]. T‐GCN: Temporal GCN [7] combines the graph convolution network and gated recurrent unit. DCRNN: Diffusion Convolutional Recurrent Neural Network [6], which combines recurrent neural networks with diffusion convolution modeling both inflow and outflow relationships. STGCN: Spatial‐Temporal Graph Convolution Network [4], which applies purely convolutional structures to extract spatial‐temporal features simultaneously from graph‐structured time series. GaAN: Gated Attention Networks [44], uses a multi‐head attention‐based network with a convolutional sub‐network to control each attention head's importance. Graph WaveNet: A convolution network architecture [5], which introduces a self‐adaptive graph to capture the hidden spatial dependency, and uses dilated convolution to capture the temporal dependency. APTN: Attention‐based Periodic‐Temporal neural Network [31], which is an end‐to‐end solution for traffic forecasting that captures spatial, short‐term, and long‐term periodical dependencies. ST‐GRAT: Spatiao‐Temporal GRaph ATtention [33], which uses spatial attention, temporal attention, and spatial sentinel vectors to capture the spatiotemporal dynamic in road networks. …”

SGDAN—A Spatio-Temporal Graph Dual-Attention Neural Network for Quantified Flight Delay Prediction

“…Recently, lots of researchers have studies dual-attention graph neural networks [ 37 , 38 ] and developed a serious of application for general spatio-temporal network in different urban traffic scene [ 39 , 40 ].…”

A Deep Learning Approach for Flight Delay Prediction Through Time-Evolving Graphs

“…More specifically, the graph convolutional neural network (GCN), with the capability of extracting complex non-linear relationships in general graphs, brings opportunities in handling complicated traffic forecasting problems with the consideration of graphstructured information [29]- [32]. Recently, based on GCN models, researchers have proposed a series of intelligent methods to provide quantified diagnostics for ground transportation [33]- [35]. Yu et al [36] utilized a recurrent neural network to model the sequential data and developed a deep neural network based on long short term memory units for traffic forecasting.…”