3DGCN: 3-Dimensional Dynamic Graph Convolutional Network for Citywide Crowd Flow Prediction

• Published in: ACM transactions on knowledge discovery from data 2021-06, Vol.15 (6), p.1-21, Article 110
• Main Authors: Xia, Tong, Lin, Junjie, Li, Yong, Feng, Jie, Hui, Pan, Sun, Funing, Guo, Diansheng, Jin, Depeng
• Format: Article
• Language: English
• Subjects: Data mining; Empirical studies in ubiquitous and mobile computing 10010405.10010481.10010485 Applied computing Transportation; Human-centered computing Applied computing; Information systems
• ISSN: 1556-4681; 1556-472X
• DOI: 10.1145/3451394

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-Dimensional Graph Convolution Network (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.