arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.18535cs.LGcs.DB
收藏

面向时空插补的图结构学习:适应节点与特征尺度

Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales

School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)计算机科学与技术学院)

Xinyu Yang, Yu Sun, Xinyang Chen, Ying Zhang, Xiaojie Yuan

AI总结:

针对固定空间图难以表达多特征异质相关性的问题,提出多尺度 GSLI 框架,通过节点/特征尺度图学习、显著性建模及跨特征跨时间表示提升时空缺失值插补性能。

摘要:

跨不同地理位置收集的时空数据往往存在缺失值,给数据分析带来挑战。现有方法主要利用固定空间图来插补缺失值,这隐含地假设不同位置的所有特征具有大致相同的空间关系。然而,这些方法可能忽略了不同位置传感器记录的多样化特征所具有的不同空间关系。为解决这一问题,我们提出用于时空插补的多尺度图结构学习框架 GSLI,该框架能够动态适应异质空间相关性。我们的框架包含节点尺度图结构学习,以适应不同特征各自独特的全局空间相关性;同时包含特征尺度图结构学习,以揭示所有站点内不同特征之间共有的空间相关性。通过结合显著性建模,该框架在插补过程中强调更重要的节点和特征。此外,GSLI 融入跨特征和跨时间表示学习,以捕捉时空依赖关系。在六个真实的不完整时空数据集上进行评估,GSLI 展现出数据插补效果的提升。

英文摘要:

Spatial-temporal data collected across different geographic locations often suffer from missing values, posing challenges to data analysis. Existing methods primarily leverage fixed spatial graphs to impute missing values, which implicitly assume that the spatial relationship is roughly the same for all features across different locations. However, they may overlook the different spatial relationships of diverse features recorded by sensors in different locations. To address this, we introduce the multi-scale Graph Structure Learning framework for spatial-temporal Imputation (GSLI) that dynamically adapts to the heterogeneous spatial correlations. Our framework encompasses node-scale graph structure learning to cater to the distinct global spatial correlations of different features, and feature-scale graph structure learning to unveil common spatial correlation across features within all stations. Integrated with prominence modeling, our framework emphasizes nodes and features with greater significance in the imputation process. Furthermore, GSLI incorporates cross-feature and cross-temporal representation learning to capture spatial-temporal dependencies. Evaluated on six real incomplete spatial-temporal datasets, GSLI showcases the improvement in data imputation.

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。

↑