SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting.

Yue Jiang, Xiucheng Li, Yile Chen, Shuai Liu, Weilong Kong, Antonis F. Lentzakis, Gao Cong.

SAGDFN is a Scalable Adaptive Graph Diffusion Forecasting Network designed to efficiently model complex spatial-temporal correlations for large-scale multivariate time series forecasting without relying on prior knowledge of spatial structure.