AI RESEARCH
Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
arXiv CS.AI
•
ArXi:2605.11178v1 Announce Type: cross Neural Sheaf Diffusion (NSD) generalizes diffusion-based Graph Neural Networks by replacing scalar graph Laplacians with sheaf Laplacians whose learned restriction maps define a task-adapted geometry. While the diffusion limit of NSD is known to be the space of global sections, the representation-theoretic structure of this harmonic space remains largely implicit. We develop a quiver-theoretic interpretation of NSD by identifying cellular sheaves on graphs with representations of the associated incidence quiver.