STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting
By Lei Bai, Lina Yao, Salil S. Kanhere, Xianzhi Wang, Quan.Z Sheng. International Joint Conference on Artificial Intelligence, 2019
308 citations recorded by the source corpus.
Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger demand prediction based on a graph and use a hierarchical graph convolutional structure to capture both spatial and temporal correlations simultaneously. Our model consists of three parts: 1) a long-term encoder to encode historical passenger demands; 2) a short-term encoder to derive the next-step prediction for generating multi-step prediction; 3) an attention-based output module to model the dynamic temporal and channel-wise information. Experiments on three real-world datasets show that our model consistently outperforms many baseline methods and state-of-the-art models.
Subfields: Building and Construction, Transportation
View Paper: https://www.semanticscholar.org/paper/5c2367ff962762905a2dad774e498d47e3e76021
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Building and Construction
- Shengna Guo
- Youfang Lin
- Huaiyu Wan
- Nizar Bouguila
- Saeed Rahmani
- Asiye Baghbani
- Zachary Patterson
- Hwangyong Choi
In Transportation
- Nizar Bouguila
- Saeed Rahmani
- Asiye Baghbani
- Zachary Patterson
- Shengna Guo
- Youfang Lin
- Huaiyu Wan
- Geoffrey I. Webb
Citations in the corpus
- Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “Bai et al. [51] proposed a framework, namely spatial-temporal graph to sequence model (STG2Seq) for multi-step city-wide passenger demand forecasting.”
- Graph Neural Network for Traffic Forecasting: A Survey (2021, unknown): “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]”
- A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, background): “, STSGCN [90] and STG2Seq [138]), or utilizing the concept of temporal message passing (e.”
- Graph Neural Controlled Differential Equations for Traffic Forecasting (2021, methodology): “STG2Seq (Bai et al. 2019) uses a multiple gated graph convolutional module and a seq2seq architecture with an attention mechanisms to make multi-step prediction.”
- Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting (2020, methodology): “DCRNN, STGCN, ASTGCN(r), STG2Seq and our STSGCN all take advantages of spatial information, so they have better performance than the methods only for time series prediction.”
- Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting (2020, methodology): “, PoI information) [7, 14] or traffic series itself [3].”