Incorporating graph neural network into route choice model

2025-03-04

AI Summary

Path choice models are often constrained by the Independence of Irrelevant Alternatives (IIA) assumption, leading to a trade-off between predictive accuracy and interpretability. To address this, we propose a hybrid modeling framework that integrates Recursive Logit (RL) with Graph Neural Networks (GNNs). This work is the first to incorporate GNNs into path choice modeling; we theoretically demonstrate that GNNs automatically capture higher-order topological dependencies and cross-path interactions in road networks, thereby relaxing the IIA constraint without requiring strong prior assumptions. Driven by trajectory data, the model is evaluated on a full-day Tokyo mobility dataset. Results show significant improvements in prediction accuracy over both standard Logit and pure RL baselines. Moreover, interpretability is enhanced via GNN-based attention mechanisms and path-level embeddings. Our approach establishes a new paradigm for transportation behavior modeling that jointly achieves high predictive performance and structural interpretability.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Route choice models are one of the most important foundations for transportation research. Traditionally, theory-based models have been utilized for their great interpretability, such as logit models and Recursive logit models. More recently, machine learning approaches have gained attentions for their better prediction accuracy. In this study, we propose novel hybrid models that integrate the Recursive logit model with Graph Neural Networks (GNNs) to enhance both predictive performance and model interpretability. To the authors' knowldedge, GNNs have not been utilized for route choice modeling, despite their proven effectiveness in capturing road network features and their widespread use in other transportation research areas. We mathematically show that our use of GNN is not only beneficial for enhancing the prediction performance, but also relaxing the Independence of Irrelevant Alternatives property without relying on strong assumptions. This is due to the fact that a specific type of GNN can efficiently capture multiple cross-effect patterns on networks from data. By applying the proposed models to one-day travel trajectory data in Tokyo, we confirmed their higher prediction accuracy compared to the existing models.

Problem

• Enhance route choice model accuracy and interpretability.
• Integrate Recursive Logit with Graph Neural Networks.
• Capture road network features without strong assumptions.

Innovation

• Integrates Recursive Logit with Graph Neural Networks
• Enhances prediction accuracy and model interpretability
• Captures multiple cross-effect patterns on networks