Hierarchical Frequency-Decomposition Graph Neural Networks for Road Network Representation Learning
This work addresses the problem of road network representation learning for intelligent transportation systems, offering a novel method that improves modeling capacity for both global trends and local fluctuations.
The paper tackled the challenge of learning effective representations for road networks by addressing the spatial-spectral misalignment in existing graph neural networks, proposing HiFiNet which demonstrated superior performance and generalization across multiple real-world datasets and downstream tasks.
Road networks are critical infrastructures underpinning intelligent transportation systems and their related applications. Effective representation learning of road networks remains challenging due to the complex interplay between spatial structures and frequency characteristics in traffic patterns. Existing graph neural networks for modeling road networks predominantly fall into two paradigms: spatial-based methods that capture local topology but tend to over-smooth representations, and spectral-based methods that analyze global frequency components but often overlook localized variations. This spatial-spectral misalignment limits their modeling capacity for road networks exhibiting both coarse global trends and fine-grained local fluctuations. To bridge this gap, we propose HiFiNet, a novel hierarchical frequency-decomposition graph neural network that unifies spatial and spectral modeling. HiFiNet constructs a multi-level hierarchy of virtual nodes to enable localized frequency analysis, and employs a decomposition-updating-reconstruction framework with a topology-aware graph transformer to separately model and fuse low- and high-frequency signals. Theoretically justified and empirically validated on multiple real-world datasets across four downstream tasks, HiFiNet demonstrates superior performance and generalization ability in capturing effective road network representations.