新模型融合时空模式，提升交通预测精度
STPFormer: A State-of-the-Art Pattern-Aware Spatio-Temporal Transformer for Traffic Forecasting
- 引入模式感知的时序与空间编码机制
- 在五个真实数据集上均达到最新最好效果
- 适合交通预测、城市计算等场景研究者
由于复杂的时序模式、动态的空间结构和多样的输入格式，时空交通预测具有挑战性。尽管基于Transformer的模型具备强大的全局建模能力，但通常存在时序编码僵化和时空融合弱的问题。我们提出STPFormer，一种时空模式感知的Transformer模型，通过统一且可解释的表征学习实现当前最优性能。该模型包含四个模块：用于模式感知时序编码的时序位置聚合器（TPA）、用于序列化空间学习的空间序列聚合器（SSA）、用于跨域对齐的时空图匹配（STGM）以及用于多尺度融合的注意力混合器（Attention Mixer）。在五个真实世界数据集上的实验表明，STPFormer持续取得新的最先进结果；消融实验与可视化验证了其有效性和泛化能力。
原文摘要 · Abstract (English)
Spatio-temporal traffic forecasting is challenging due to complex temporal patterns, dynamic spatial structures, and diverse input formats. Although Transformer-based models offer strong global modeling, they often struggle with rigid temporal encoding and weak space-time fusion. We propose STPFormer, a Spatio-Temporal Pattern-Aware Transformer that achieves state-of-the-art performance via unified and interpretable representation learning. It integrates four modules: Temporal Position Aggregator (TPA) for pattern-aware temporal encoding, Spatial Sequence Aggregator (SSA) for sequential spatial learning, Spatial-Temporal Graph Matching (STGM) for cross-domain alignment, and an Attention Mixer for multi-scale fusion. Experiments on five real-world datasets show that STPFormer consistently sets new SOTA results, with ablation and visualizations confirming its effectiveness and generalizability.
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。