Development of a graph neural network surrogate for travel demand modelling

2024-08-14

AI Summary

To address the limited expressiveness and prediction instability of conventional travel demand modeling, this paper proposes a graph neural network–based surrogate modeling approach for mobility demand. Methodologically, we (1) design GATv3—a novel Graph Attention Network variant incorporating residual connections to mitigate oversmoothing in deep GATs; (2) replace standard regression with a fine-grained classification framework to enhance interpretability, prediction stability, and discriminative capability for high-resolution tasks; and (3) introduce a traffic-aware synthetic data generation strategy to improve model generalization. Experimental results demonstrate that GATv3 achieves substantial gains in classification accuracy, while GCN—when augmented with synthetic data—surpasses baseline performance on fine-grained demand prediction. Crucially, the proposed classification paradigm better aligns with real-world applications requiring strong discriminative power, such as link-level traffic control and congestion early warning.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

As urban environments grow, the modelling of transportation systems becomes increasingly complex. This paper advances the field of travel demand modelling by introducing advanced Graph Neural Network (GNN) architectures as surrogate models, addressing key limitations of previous approaches. Building on prior work with Graph Convolutional Networks (GCNs), we introduce GATv3, a new Graph Attention Network (GAT) variant that mitigates over-smoothing through residual connections, enabling deeper and more expressive architectures. Additionally, we propose a fine-grained classification framework that improves predictive stability while achieving numerical precision comparable to regression, offering a more interpretable and efficient alternative. To enhance model performance, we develop a synthetic data generation strategy, which expands the augmented training dataset without overfitting. Our experiments demonstrate that GATv3 significantly improves classification performance, while the GCN model shows unexpected dominance in fine-grained classification when supplemented with additional training data. The results highlight the advantages of fine-grained classification over regression for travel demand modelling tasks and reveal new challenges in extending GAT-based architectures to complex transport scenarios. Notably, GATv3 appears well-suited for classification-based transportation applications, such as section control and congestion warning systems, which require a higher degree of differentiation among neighboring links. These findings contribute to refining GNN-based surrogates, offering new possibilities for applying GATv3 and fine-grained classification in broader transportation challenges.

Problem

• Develops GATv3 to improve travel demand modeling accuracy.
• Introduces fine-grained classification for better predictive stability.
• Proposes synthetic data generation to prevent model overfitting.

Innovation

• GATv3 mitigates over-smoothing with residual connections
• Fine-grained classification improves predictive stability
• Synthetic data generation enhances model performance