Dual-norm based dynamic graph diffusion network for temporal prediction

doi:10.1016/j.ipm.2023.103387

Dual-norm based dynamic graph diffusion network for temporal prediction

2023-07-01

2

PRE

AI

DOI：10.1016/j.ipm.2023.103387

Original

Original request for help

Save

Abstract

En 中文

Precise prediction of Multivariate Time Series (MTS) has been playing a pivotal role in numerous kinds of applications. Existing works have made significant efforts to capture temporal tendency and periodical patterns, but they always ignore abrupt variations and heterogeneous/spatial associations of sensory data. In this paper, we develop a dual normalization (dual-norm) based dynamic graph diffusion network (DNGDN) to capture hidden intricate correlations of MTS data for temporal prediction. Specifically, we design time series decomposition and dual-norm mechanism to learn the latent dependencies and alleviate the adverse effect of abnormal MTS data. Furthermore, a dynamic graph diffusion network is adopted for adaptively exploring the spatial correlations among variables. Extensive experiments are performed on 3 real world experimental datasets with 8 representative baselines for temporal prediction. The performances of DNGDN outperforms all baselines with at least 4% lower MAPE over all datasets.

Keywords:

Intelligent systems

Graph diffusion network

Spatio-temporal learning

Time series forecasting

Dual-norm based dynamic graph diffusion network for temporal prediction

Abstract

Journal

Organization