5 papers · 1 filter
Sheaf-MPNN: A Library for Sheaf Neural Networks as Message Passing
Alessio Borgi, Mario Severino, Luke Braithwaite +14
Standard Graph Neural Networks (GNNs) implicitly assume that neighboring nodes share the same feature space, which contributes to oversmoothing and poor performance on heterophilic…
Let the Heads Talk: Beyond Diagonal Graph Attention
Riccardo Ali, Alessio Borgi, Mario Severino +4
Sheaf Neural Networks generalize scalar-weighted message passing by replacing scalar edge weights with linear transport maps between local feature spaces. Yet the role of this matr…
Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs
Alessio Borgi, Mario Severino, Fabrizio Silvestri +1
Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how vector information can be trans…
Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces
Mario Severino, Manuela Moretto, Robert A. McCutcheon +1
Correlation matrices are fundamental summaries of functional brain networks, yet standard analyses often treat entries independently, ignoring the curved geometry of correlation sp…
Remember to Forget: Gated Adaptive Positional Encoding
Riccardo Ali, Alessio Borgi, Christopher Irwin +2
Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can ente…