Pietro Liò

Benchmarking Sheaf Neural Networks for Inductive Tasks

This work addresses the first systematic benchmark of the sheaf design space through evaluating three diffusion mechanisms (neural sheaf diffusion, sheaf attention, and sheaf attention with Graph Attention Network v2), three restriction-map parameterizations, three stalk dimensions, and six modern GNN architectural components, within a message-passing reformulation that never assembles the heavy sheaf Laplacian.