HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting

Abstract

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.

References in corpus (7)

• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
• A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
• Predicting Urban Water Quality with Ubiquitous Data

Cited by in corpus (5)

• ST-GRAT: A Novel Spatio-temporal Graph Attention Network for Accurately Forecasting Dynamically Changing Road Speed
• Principled Weight Initialization for Hypernetworks
• Causal Inference for Time series Analysis: Problems, Methods and Evaluation
• DHP: Differentiable Meta Pruning via HyperNetworks
• Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworks