Hierarchical Graph Structures for Congestion and ETA Prediction

2022/11/21 by Florian Grötschla, Grötschla, Florian, Joël Mathys +1
Computer Science · Engineering · Social Sciences · #Artificial Intelligence (cs.AI) #Data Management and Algorithms #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Machine Learning (cs.LG) #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2211.11762

openalex publication_date 2022/11/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Traffic4cast is an annual competition to predict spatio temporal traffic based on real world data. We propose an approach using Graph Neural Networks that directly works on the road graph topology which was extracted from OpenStreetMap data. Our architecture can incorporate a hierarchical graph representation to improve the information flow between key intersections of the graph and the shortest paths connecting them. Furthermore, we investigate how the road graph can be compacted to ease the flow of information and make use of a multi-task approach to predict congestion classes and ETA simultaneously. Our code and models are released here: https://github.com/floriangroetschla/NeurIPS2022-traffic4cast

Related

• MHGNet: Multi-Heterogeneous Graph Neural Network for Traffic Prediction
• GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction
• STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Prediction
• Unboxing the graph: Neural Relational Inference for Mobility Prediction
• Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors