Skip to content

Spatio-temporal sheaf diffusion (ST-Sheaf GNN)

Home / Concepts / Spatio-temporal sheaf diffusion (ST-Sheaf GNN)

Spatio-temporal sheaf diffusion (ST-Sheaf GNN)

Auto-generated stub. Edit this file to add more details.

A graph neural network framework for spatio-temporal forecasting that models information flow via dynamic restriction maps within sheaf-theoretic vector spaces.

Why It Matters

It provides a novel topological approach to spatio-temporal modeling that addresses the limitations of standard message passing and oversmoothing.

Evidence

We introduce a spatio-temporal sheaf diffusion graph neural network (ST-Sheaf GNN) that embeds graph topology into sheaf-theoretic vector spaces connected by learned linear restriction maps.

Metadata & Links