arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2506.08054cs.LGcs.AI
收藏

STAMImputer：用于交通数据插补的时空注意力 MoE

STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation

School of Cyber Science and Technology, Beihang University（北航信息科学与技术学院）；Hangzhou Innovation Institute of BUAA, Hangzhou, China（北京航空航天大学杭州创新研究院）；Department of Computer Science and Technology, Shantou University（汕头大学计算机科学与技术学院）；School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Department of Computing, Macquarie University（麦考瑞大学计算机学院）；National University of Defense Technology, Changsha, China（国防科技大学）

Yiming Wang, Hao Peng, Senzhang Wang, Haohua Du, Chunyang Liu, Jia Wu, Guanlin Wu

备注：
10 pages, 5 figures, 3 tables. Extended version of paper accepted at IJCAI 2025
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对交通数据块状缺失与非平稳分布漂移问题，提出 STAMImputer，结合 MoE 与 LrSGAT 动态图机制，在四个数据集上显著优于现有 SOTA。

摘要：

交通数据插补对于支撑智能交通系统中的各类应用（例如交通流量预测）具有根本性的重要意义。然而，现有的时间到空间序列方法在块状缺失数据场景中往往无法有效提取特征。同时，用于空间特征传播的静态图结构显著限制了模型在处理非平稳交通数据分布漂移问题时的灵活性。为解决这些问题，本文提出了一种名为 STAMImputer 的时空注意力专家混合网络，用于交通数据插补。具体而言，我们引入 Mixture of Experts（MoE，专家混合）框架来捕获潜在的时空特征及其影响权重，从而有效插补块状缺失。一种新颖的 Low-rank guided Sampling Graph ATtention（LrSGAT，低秩引导采样图注意力）机制被设计用于动态平衡路网中的局部与全局相关性。采样得到的注意力向量被用于生成动态图，以捕获实时空间相关性。本文在四个交通数据集上开展了大量实验进行评估。结果表明，与现有 SOTA 方法相比，STAMImputer 实现了显著的性能提升。我们的代码可在 https://github.com/RingBDStack/STAMImupter 获取。

英文摘要：

Traffic data imputation is fundamentally important to support various applications in intelligent transportation systems such as traffic flow prediction. However, existing time-to-space sequential methods often fail to effectively extract features in block-wise missing data scenarios. Meanwhile, the static graph structure for spatial feature propagation significantly constrains the models flexibility in handling the distribution shift issue for the nonstationary traffic data. To address these issues, this paper proposes a SpatioTemporal Attention Mixture of experts network named STAMImputer for traffic data imputation. Specifically, we introduce a Mixture of Experts (MoE) framework to capture latent spatio-temporal features and their influence weights, effectively imputing block missing. A novel Low-rank guided Sampling Graph ATtention (LrSGAT) mechanism is designed to dynamically balance the local and global correlations across road networks. The sampled attention vectors are utilized to generate dynamic graphs that capture real-time spatial correlations. Extensive experiments are conducted on four traffic datasets for evaluation. The result shows STAMImputer achieves significantly performance improvement compared with existing SOTA approaches. Our codes are available at https://github.com/RingBDStack/STAMImupter.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑