用事故数据提升交通预测，模型更准更快。
Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting
- 引入事故与管制数据，构建条件化时空建模框架
- 在东京和加州数据集上优于SOTA模型，参数少、算力低
- 适合城市交通规划与智能驾驶系统研发者
交通预测是时空数据挖掘中的关键挑战，尽管深度学习取得进展，但外部因素如交通事故和交通管制的影响常被忽略，导致预测不准。为此，我们构建了来自东京和加州的两个增强型交通数据集，整合了交通事故和交通管制信息。基于这些数据，提出ConFormer（条件变压器）框架，结合图传播与引导归一化层，根据历史模式动态调整时空节点关系，提升预测精度。该模型在预测性能和效率上均超越当前最优模型STAEFormer，计算成本更低，参数需求更少。大量实验表明，ConFormer在多个指标上持续优于主流时空基线模型，展现出推动交通预测研究的巨大潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。