Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting

TL;DR

This paper introduces ConFormer, a novel transformer-based framework that incorporates accident and regulation data into traffic forecasting, significantly improving accuracy and efficiency over existing models.

Contribution

The paper presents ConFormer, a new conditional transformer model that integrates external accident and regulation data with graph propagation for enhanced traffic prediction.

Findings

ConFormer outperforms state-of-the-art models in accuracy.

It achieves lower computational costs and fewer parameters.

Extensive evaluations confirm its robustness across datasets.

Abstract

Traffic prediction remains a key challenge in spatio-temporal data mining, despite progress in deep learning. Accurate forecasting is hindered by the complex influence of external factors such as traffic accidents and regulations, often overlooked by existing models due to limited data integration. To address these limitations, we present two enriched traffic datasets from Tokyo and California, incorporating traffic accident and regulation data. Leveraging these datasets, we propose ConFormer (Conditional Transformer), a novel framework that integrates graph propagation with guided normalization layer. This design dynamically adjusts spatial and temporal node relationships based on historical patterns, enhancing predictive accuracy. Our model surpasses the state-of-the-art STAEFormer in both predictive performance and efficiency, achieving lower computational costs and reduced parameter demands. Extensive evaluations demonstrate that ConFormer consistently outperforms mainstream spatio-temporal baselines across multiple metrics, underscoring its potential to advance traffic prediction research.