GEnSHIN: Graphical Enhanced Spatio-temporal Hierarchical Inference Network for Traffic Flow Prediction

2026-01-08

arXiv.org

AI Summary

This work proposes a graph-enhanced spatiotemporal hierarchical inference network to address the insufficient modeling of complex spatiotemporal dependencies in urban traffic flow prediction, particularly the poor stability during morning and evening peak hours. The proposed architecture integrates attention-augmented Graph Convolutional Recurrent Units (GCRUs), an asymmetric dual-embedding graph generation mechanism, and a learnable prototype-based dynamic memory bank to effectively capture both the underlying road network topology and its dynamic evolution. Evaluated on the METR-LA dataset, the model achieves or surpasses state-of-the-art performance across standard metrics—including MAE, RMSE, and MAPE—and demonstrates significantly improved prediction stability during peak traffic periods.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

With the acceleration of urbanization, intelligent transportation systems have an increasing demand for accurate traffic flow prediction. This paper proposes a novel Graph Enhanced Spatio-temporal Hierarchical Inference Network (GEnSHIN) to handle the complex spatio-temporal dependencies in traffic flow prediction. The model integrates three innovative designs: 1) An attention-enhanced Graph Convolutional Recurrent Unit (GCRU), which strengthens the modeling capability for long-term temporal dependencies by introducing Transformer modules; 2) An asymmetric dual-embedding graph generation mechanism, which leverages the real road network and data-driven latent asymmetric topology to generate graph structures that better fit the characteristics of actual traffic flow; 3) A dynamic memory bank module, which utilizes learnable traffic pattern prototypes to provide personalized traffic pattern representations for each sensor node, and introduces a lightweight graph updater during the decoding phase to adapt to dynamic changes in road network states. Extensive experiments on the public dataset METR-LA show that GEnSHIN achieves or surpasses the performance of comparative models across multiple metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). Notably, the model demonstrates excellent prediction stability during peak morning and evening traffic hours. Ablation experiments further validate the effectiveness of each core module and its contribution to the final performance.

Problem

• traffic flow prediction
• spatio-temporal dependencies
• intelligent transportation systems
• urbanization

Innovation

• Graph Convolutional Recurrent Unit
• Asymmetric Graph Generation
• Dynamic Memory Bank
• Spatio-temporal Traffic Prediction
• Transformer-enhanced Attention