FUSE-Traffic: Fusion of Unstructured and Structured Data for Event-aware Traffic Forecasting

2025-10-16

AI Summary

Existing traffic forecasting models rely heavily on structured data and struggle to effectively model unstructured, sporadic events—such as traffic accidents—due to poor generalizability and weak semantic expressiveness of handcrafted event features. Method: We propose an event-aware graph neural network framework that jointly encodes unstructured event semantics (e.g., textual incident descriptions) and structured spatiotemporal traffic data (e.g., road topology and flow dynamics) in an end-to-end manner, without manual feature engineering. It incorporates cross-modal attention and dynamic graph reconstruction to enable event-driven spatiotemporal dependency modeling. Contribution/Results: Extensive experiments on multiple benchmark datasets demonstrate that our model significantly improves prediction accuracy under突发事件 (e.g., average MAE reduced by 12.7%), while exhibiting strong generalizability and robustness. This work establishes a novel paradigm for real-time, event-responsive urban traffic forecasting.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Reasoning under Uncertainty: Graphical Models

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
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Accurate traffic forecasting is a core technology for building Intelligent Transportation Systems (ITS), enabling better urban resource allocation and improved travel experiences. With growing urbanization, traffic congestion has intensified, highlighting the need for reliable and responsive forecasting models. In recent years, deep learning, particularly Graph Neural Networks (GNNs), has emerged as the mainstream paradigm in traffic forecasting. GNNs can effectively capture complex spatial dependencies in road network topology and dynamic temporal evolution patterns in traffic flow data. Foundational models such as STGCN and GraphWaveNet, along with more recent developments including STWave and D2STGNN, have achieved impressive performance on standard traffic datasets. These approaches incorporate sophisticated graph convolutional structures and temporal modeling mechanisms, demonstrating particular effectiveness in capturing and forecasting traffic patterns characterized by periodic regularities. To address this challenge, researchers have explored various ways to incorporate event information. Early attempts primarily relied on manually engineered event features. For instance, some approaches introduced manually defined incident effect scores or constructed specific subgraphs for different event-induced traffic conditions. While these methods somewhat enhance responsiveness to specific events, their core drawback lies in a heavy reliance on domain experts' prior knowledge, making generalization to diverse and complex unknown events difficult, and low-dimensional manual features often lead to the loss of rich semantic details.

Problem

• Fusing unstructured and structured data for traffic forecasting
• Addressing limitations of manual event feature engineering
• Improving generalization to complex unknown traffic events

Innovation

• Fuses unstructured and structured traffic data
• Integrates event information for traffic forecasting
• Enhances model generalization to unknown events