解决时空数据缺失问题，提升预测准确性和泛化能力。
STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach
- 分阶段感知时间偏移，动态建模空间关系。
- 在九个数据集上表现优于现有方法，显著提升预测精度。
- 适合传感器数据不全的环境监测、城市交通等场景。
时空任务常因传感器缺失或不可访问导致数据不完整，时空克里金法对填补完整时间信息至关重要。然而，现有模型难以确保推断出的时空模式的有效性与泛化能力，尤其在捕捉动态空间依赖和时间偏移方面存在不足，且对未知传感器的泛化优化有限。为此，我们提出基于图神经网络的时空克里金框架 STA-GANN，通过三个核心模块：(i) 分离式时序相位模块，用于感知并校正时间戳偏移；(ii) 动态数据驱动元图建模，利用时间数据与元信息更新空间关系；(iii) 对抗式迁移学习策略，保障模型泛化性。在来自四个领域的九个数据集上进行广泛验证，并结合理论分析，证明了 STA-GANN 的优越性能。
原文摘要 · Abstract (English)
Spatio-temporal tasks often encounter incomplete data arising from missing or inaccessible sensors, making spatio-temporal kriging crucial for inferring the completely missing temporal information. However, current models struggle with ensuring the validity and generalizability of inferred spatio-temporal patterns, especially in capturing dynamic spatial dependencies and temporal shifts, and optimizing the generalizability of unknown sensors. To overcome these limitations, we propose Spatio-Temporal Aware Graph Adversarial Neural Network (STA-GANN), a novel GNN-based kriging framework that improves spatio-temporal pattern validity and generalization. STA-GANN integrates (i) Decoupled Phase Module that senses and adjusts for timestamp shifts. (ii) Dynamic Data-Driven Metadata Graph Modeling to update spatial relationships using temporal data and metadata; (iii) An adversarial transfer learning strategy to ensure generalizability. Extensive validation across nine datasets from four fields and theoretical evidence both demonstrate the superior performance of STA-GANN.
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。