Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting

By Xu Geng, Yaguang Li, Leye Wang, Lingyu Zhang, Qiang Yang, Jieping Ye, Yan Liu. AAAI Conference on Artificial Intelligence, 2019

878 citations recorded by the source corpus.

Region-level demand forecasting is an essential task in ridehailing services. Accurate ride-hailing demand forecasting can guide vehicle dispatching, improve vehicle utilization, reduce the wait-time, and mitigate traffic congestion. This task is challenging due to the complicated spatiotemporal dependencies among regions. Existing approaches mainly focus on modeling the Euclidean correlations among spatially adjacent regions while we observe that non-Euclidean pair-wise correlations among possibly distant regions are also critical for accurate forecasting. In this paper, we propose the spatiotemporal multi-graph convolution network (ST-MGCN), a novel deep learning model for ride-hailing demand forecasting. We first encode the non-Euclidean pair-wise correlations among regions into multiple graphs and then explicitly model these correlations using multi-graph convolution. To utilize the global contextual information in modeling the temporal correlation, we further propose contextual gated recurrent neural network which augments recurrent neural network with a contextual-aware gating mechanism to re-weights different historical observations. We evaluate the proposed model on two real-world large scale ride-hailing demand datasets and observe consistent improvement of more than 10% over stateof-the-art baselines.

Subfields: Automotive Engineering, Building and Construction, Transportation

View Paper: https://www.semanticscholar.org/paper/0f8332fb651bf639ab110c65067ef2225f49eea5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Building and Construction

In Transportation

Citations in the corpus

Graph Neural Network for Traffic Forecasting: A Survey (2021, neutral): “Ride-hailing Demand [187], [188], [189], [190], [191], [192], [193], [194], [195], [196], [197] Taxi Demand [192], [193], [195], [198], [199], [200], [201], [202], [203], [204], [205], [206], [207] Shared Vehicle Demand [208]”
Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting (2021, background): “RNN-based STGNNs employ recurrent units to store historical information and replace the original linear projections in the recurrent units with graph convolution operations [6], [7], [8], [37].”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “• Neighborhood: This kind of adjacency matrix is suitable for graphs whose nodes have been defined as zones or grids [50], [63].”
Spatio-Temporal Meta-Graph Learning for Traffic Forecasting (2022, neutral): “Third, motivated by (Vaswani et al. 2017), a series of traffic trans-formers (Zheng et al. 2020; Xu et al. 2020) and time series transformers (Li et al. 2019; Zhou et al. 2021; Xu et al. 2021) were proposed to do the long sequence time series modeling.”
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting (2020, methodology): “, PoI information) [7, 14] or traffic series itself [3].”
Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics (2020, background): “Modeling real world phenomena, such as climate observations, trafﬁc ﬂow, physics and chemistry simulation (Li et al., 2018; Geng et al., 2019; Long et al., 2018; de Bezenac et al., 2018; Sanchez-Gonzalez et al., 2018; Gilmer et al., 2017), is important but extremely challenging.”
Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting (2018, background): “Several studies [50], [51] also incorporated multi-scale graph convolution operations into their proposed models to learn traffic features.”
Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends (2020, methodology): “Within the applications we have surveyed, attention has been used to perform message passing within graph NNs [31], [54], to focus on different nodes within combinatorial problems [95], [13], [75], and to aggregate context across local trajectory segments when estimating the travel time [97].”
Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting (2021, background): “Some works [4, 12] took a further step to consider multiple types of correlations between nodes include distance, Pearson Correlation Coefficient of historical data, functional similarity and interactions between each pair of nodes.”
Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey (2023, background): “have been proposed to address this challenge [17], [19], [20], [23], [31], [165]–[169].”
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, methodology): “DCRNN [71] 2018 ICLR M-S D-C Spatial GNN T-R No R SP STGCN [58] 2018 IJCAI M-S D-F Spectral GNN T-C No R SP ST-MetaNet [73] 2019 KDD M-S D-F Spatial GNN T-R No R SP, PC NGAR [74] 2019 IEEE IJCNN S-S D-F Spatial GNN T-R No R ASTGCN [75] 2019 AAAI M-S D-F Spectral GNN T-H No R SP, PC ST-MGCN [46] 2019”
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution (2021, methodology): “It is obvious that traffic condition can be significantly affected or inferred by external factors such as weather [33, 35] and POI [7, 17], which need extra collection and preprocessing.”
High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting (2018, background): “Several studies [51][52] also incorporated multi-scale graph convolution operations into their proposed models to learn traffic features.”
Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, neutral): “Application domains Related works Transportation [177], [187], [116], [31], [29], [6], [32], [127], [53], [112], [26], [105], [166], [82], [23], [66], [108], [126], [81], [139], [78], [128], [146], [148], [72], [98], [189], [22], [24], [99], [96], [16], [97], [85], [15], [164], [165], [95], [140], [”
Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions (2021, background): “[52] ﬁrst used graphs to encode different kinds of correlations among regions, including neighborhood, functional similarity, and transportation connectivity.”