Open data is frequently released spatially aggregated, usually to comply with privacy policies. But coarse, heterogeneous aggregations complicate learning and integration for downstream AI/ML systems. In this work, we consider models to disaggregate spatio-temporal data from a low-resolution, irregular partition (e.g., census tract) to a high-resolution, irregular partition (e.g., city block). We propose a model, Gated Recurrent Unit with Spatial Attention ($GRU^{spa}$), where spatial attention layers are integrated into the original Gated Recurrent Unit (GRU) model. The spatial attention layers capture spatial interactions among regions, while the gated recurrent module captures the temporal dependencies. Additionally, we utilize containment relationships between different geographic levels (e.g., when a given city block is wholly contained in a given census tract) to constrain the spatial attention layers. For situations where limited historical training data is available, we study transfer learning scenarios and show that a model pre-trained on one city variable can be fine-tuned for another city variable using only a few hundred samples. Evaluating these techniques on two mobility datasets, we find that $GRU^{spa}$ provides a significant improvement over other neural models as well as typical heuristic methods, allowing us to synthesize realistic point data over small regions useful for training downstream models.

翻译：开放数据通常以空间聚合形式发布，这主要是为了遵循隐私政策。但粗粒度、异构的聚合方式会增加下游AI/ML系统的学习与集成难度。本研究提出了一种模型——基于空间注意力的门控循环单元（$GRU^{spa}$），用于将低分辨率、不规则划分（如人口普查区）的时空数据分解至高分辨率、不规则划分（如城市街区）。该模型将空间注意力层集成到原始门控循环单元（GRU）中：空间注意力层捕捉区域间的空间交互，而门控循环模块则捕获时间依赖关系。此外，我们利用不同地理层级间的包含关系（例如，当给定城市街区完全包含在给定的普查区内时）对空间注意力层进行约束。针对历史训练数据有限的情况，我们研究了迁移学习场景，并证明：在一个城市变量上预训练的模型，仅需数百个样本即可微调适配至另一个城市变量。通过在两个移动数据集上评估这些技术，我们发现$GRU^{spa}$相较于其他神经模型及典型启发式方法具有显著提升，可合成小区域内的真实点数据，用于训练下游模型。