Urban hotspot forecasting via automated spatio-temporal information fusion

Abstract

Urban hotspot forecasting is one of the most important tasks for resource scheduling and security in future smart cities. Most previous works employed fixed neural architectures based on many complicated spatial and temporal learning modules. However, designing appropriate neural architectures is challenging for urban hotspot forecasting. One reason is that there is currently no adequate support system for how to fuse multi-scale spatio-temporal information rationally by integrating different spatial and temporal learning modules. Another one is that the empirical fixed neural architecture is difficult to adapt to different data scenarios from different domains or cities. To address the above problems, we propose a novel framework based on neural architecture search for urban hotspot forecasting, namely Automated Spatio-Temporal Information Fusion Neural Network (ASTIF-Net). In the search space of our ASTIF-Net, normal convolution and graph convolution operations are adopted to capture spatial geographic neighborhood dependencies and spatial semantic neighborhood dependencies, and different types of temporal convolution operations are adopted to capture short-term and long-term temporal dependencies. In addition to combining spatio-temporal learning operations from different scales, ASTIF-Net can also search appropriate fusion methods for aggregating multi-scale spatio-temporal hidden information. We conduct extensive experiments to evaluate ASTIF-Net on three real-world urban hotspot datasets from different domains to demonstrate that our proposed model can obtain effective neural architectures and achieve superior performance (about 5%∼10% improvements) compared with the existing state-of-art baselines.