Dynamic personalized graph neural network with linear complexity for multivariate time series forecasting

Zhuolin Li, Ziheng Gao, Gaowei Zhang, Jingjing Liu, Lingyu Xu

Abstract: Highlights•Spatio-temporal graph networks with linear complexity learn graph automatically.•Dynamic personalized graph convolution enhances the influence of the nodes’ own.•Experiments on six datasets demonstrate the effectiveness of the proposed method.