HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting
This work addresses forecasting challenges in dynamic systems like air quality monitoring, offering a novel method for integrating spatial and temporal data, though it appears incremental as it builds on existing hypernetwork and ST modeling concepts.
The authors tackled spatio-temporal forecasting by proposing HyperST-Net, a hypernetwork-based framework that dynamically generates temporal module parameters from spatial characteristics, achieving significant improvements and outperforming state-of-the-art baselines in experiments on real-world tasks.
Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality readings. Forecasting over ST data is of great importance but challenging as it is affected by many complex factors, including spatial characteristics, temporal characteristics and the intrinsic causality between them. In this paper, we propose a general framework (HyperST-Net) based on hypernetworks for deep ST models. More specifically, it consists of three major modules: a spatial module, a temporal module and a deduction module. Among them, the deduction module derives the parameter weights of the temporal module from the spatial characteristics, which are extracted by the spatial module. Then, we design a general form of HyperST layer as well as different forms for several basic layers in neural networks, including the dense layer (HyperST-Dense) and the convolutional layer (HyperST-Conv). Experiments on three types of real-world tasks demonstrate that the predictive models integrated with our framework achieve significant improvements, and outperform the state-of-the-art baselines as well.