3DGCN: 3-Dimensional Dynamic Graph Convolutional Network for Citywide Crowd Flow Prediction
- 28 June 2021
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 15 (6), 1-21
- https://doi.org/10.1145/3451394
Abstract
Crowd flow prediction is an essential task benefiting a wide range of applications for the transportation system and public safety. However, it is a challenging problem due to the complex spatio-temporal dependence and the complicated impact of urban structure on the crowd flow patterns. In this article, we propose a novel framework, 3- D imensional G raph C onvolution N etwork (3DGCN), to predict citywide crowd flow. We first model it as a dynamic spatio-temporal graph prediction problem, where each node represents a region with time-varying flows, and each edge represents the origin–destination (OD) flow between its corresponding regions. As such, OD flows among regions are treated as a proxy for the spatial interactions among regions. To tackle the complex spatio-temporal dependence, our proposed 3DGCN can model the correlation among graph spatial and temporal neighbors simultaneously. To learn and incorporate urban structures in crowd flow prediction, we design the GCN aggregator to be learned from both crowd flow prediction and region function inference at the same time. Extensive experiments with real-world datasets in two cities demonstrate that our model outperforms state-of-the-art baselines by 9.6%∼19.5% for the next-time-interval prediction.Keywords
Funding Information
- National Key Research and Development Program of China (SQ2018YFB180012)
- National Nature Science Foundation of China (61971267, 61972223, 61861136003, and 61621091)
- Beijing Natural Science Foundation (L182038)
- Beijing National Research Center For Information Science And Technology (20031887521)
- singhua University—Tencent Joint Laboratory for Internet Innovation Technology
This publication has 34 references indexed in Scilit:
- A distributed spatial–temporal weighted model on MapReduce for short-term traffic flow forecastingNeurocomputing, 2016
- CityMomentumPublished by Association for Computing Machinery (ACM) ,2015
- Traffic Flow Prediction With Big Data: A Deep Learning ApproachIEEE Transactions on Intelligent Transportation Systems, 2014
- Discovering Urban Functional Zones Using Latent Activity TrajectoriesIEEE Transactions on Knowledge and Data Engineering, 2014
- Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised LearningIEEE Transactions on Intelligent Transportation Systems, 2013
- A Tale of Many Cities: Universal Patterns in Human Urban MobilityPLOS ONE, 2012
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Wavelets on graphs via spectral graph theoryApplied and Computational Harmonic Analysis, 2011
- Adaptive Seasonal Time Series Models for Forecasting Short-Term Traffic FlowTransportation Research Record: Journal of the Transportation Research Board, 2007
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998