Sheaf Diffusion with Adaptive Local Structure for Spatio-Temporal Forecasting

ArXi:2604.11275v1 Announce Type: new Spatio-temporal systems often exhibit highly heterogeneous and non-intuitive responses to localized disruptions, limiting the effectiveness of conventional message passing approaches in modeling higher-order interactions under local heterogeneity. This paper reformulates spatio-temporal forecasting as the problem of learning information flow over locally structured spaces, rather than propagating globally aligned node representations. We