分离交通数据中的周期性与突发事件，提升预测准确性
DualCast: A Model to Disentangle Aperiodic Events from Traffic Series
- 双分支结构分离周期性模式与外部突发事件
- 跨时间注意力机制捕捉高阶时空关联，误差降低最高9.6%
- 适配现有模型，适用于城市交通管理与应急响应
交通预测对交通系统优化至关重要。现有模型多以最小化平均预测误差为目标，倾向于学习训练数据中常见的周期性事件，忽视了如交通事故等关键的非周期性事件。为此，我们提出DualCast，一种双分支框架，将交通信号分解为内在时空模式和外部环境因素（包括非周期性事件）。DualCast还引入跨时间注意力机制，从周期性和非周期性模式中捕捉高阶时空关系。该模型具有通用性，可集成到多种近期交通预测模型中，在多个真实数据集上，使预测误差最高降低9.6%。源代码已公开于https://github.com/suzy0223/DualCast。
原文摘要 · Abstract (English)
Traffic forecasting is crucial for transportation systems optimisation. Current models minimise the mean forecasting errors, often favouring periodic events prevalent in the training data, while overlooking critical aperiodic ones like traffic incidents. To address this, we propose DualCast, a dual-branch framework that disentangles traffic signals into intrinsic spatial-temporal patterns and external environmental contexts, including aperiodic events. DualCast also employs a cross-time attention mechanism to capture high-order spatial-temporal relationships from both periodic and aperiodic patterns. DualCast is versatile. We integrate it with recent traffic forecasting models, consistently reducing their forecasting errors by up to 9.6% on multiple real datasets. Our source code is available at https://github.com/suzy0223/DualCast.
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。