Traffic forecasting improves by learning local and cross-region patterns
Learning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting
Machine LearningArtificial Intelligence
Summary
Traffic forecasting helps predict vehicle flow, which is important for managing roads and preventing jams. The authors developed a new method called LoReST that better understands both nearby roads and distant regions. Their method considers unique differences in roads and directions and efficiently gathers information over large areas. Tests show it predicts traffic more accurately on multiple datasets than previous approaches.
What this means in practice
- •For traffic management teams: Improve large-scale real-time traffic predictions by modeling both local road differences and regional interactions more accurately.
- •For smart city developers: Enhance intelligent transportation systems with efficient algorithms that capture both nearby and distant traffic patterns for better routing and planning.
Authors
Qi Feng, Zidong Wang, Bo Li, Xiaoguang Gao, Jiayu Zhang, Chenfeng Wang, Kaifang Wan
Abstract
Traffic flow forecasting is essential to intelligent transportation systems. Large-scale traffic forecasting requires jointly modeling local spatial dependencies and cross-region context.Spatial dependencies between geographically neighboring nodes are heterogeneous due to differences in road identity and travel direction, while acquiring global information through allpairs node interactions incurs substantial computational costs. Therefore, capturing local heterogeneity while efficiently acquiring long-range context remains an important challenge in largescale traffic forecasting. To address these challenges, we propose LoReST, a Local-Region Spatial Temporal network that models spatial dependencies at two complementary granularities: node neighborhoods and road network regions. Specifically, relation-aware local aggregation captures heterogeneous dependencies within geographic neighborhoods through road and direction specific feature transformations. Cross-region interaction constructs region representations through mean pooling, exchanges long range context via inter-region attention, and broadcasts it back to nodes. By integrating local information aggregation with crossregion interaction, LoReST is able to effectively achieve spatial dependency learning in large-scale road networks. Experiments on four datasets of the LargeST benchmark show average relative reductions of 4.78%, 3.60%, and 5.75% in MAE, RMSE, and MAPE, respectively.