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.

翻译：交通预测作为时空数据挖掘中的关键挑战，尽管深度学习已取得进展，但其准确性仍受到外部因素（如交通事故和交通管制）复杂影响的制约，现有模型常因数据整合有限而忽视这些因素。为应对这些局限，我们提出了两个来自东京和加利福尼亚的增强型交通数据集，整合了交通事故与管制数据。基于这些数据集，我们提出ConFormer（条件Transformer），这是一个创新框架，将图传播与引导归一化层相结合。该设计基于历史模式动态调整时空节点关系，从而提升预测精度。我们的模型在预测性能和效率上均超越了当前最先进的STAEFormer，实现了更低的计算成本和更少的参数需求。大量评估表明，ConFormer在多项指标上持续优于主流时空基线模型，凸显了其在推动交通预测研究方面的潜力。