6 papers
Oscillatory Neural Dynamics over Sheaves
Jan-Willem Van Looy, Alessandro Trenta, Alessio Gravina +5
Effective long-range propagation remains a central challenge in graph neural networks, as increasing a model's propagation depth does not guarantee that distant nodes effectively i…
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…
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…
Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves
Alessio Borgi, Fabrizio Silvestri, Pietro Liò
Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport ma…
Z-SASLM: Zero-Shot Style-Aligned SLI Blending Latent Manipulation
Alessio Borgi, Luca Maiano, Irene Amerini
We introduce Z-SASLM, a Zero-Shot Style-Aligned SLI (Spherical Linear Interpolation) Blending Latent Manipulation pipeline that overcomes the limitations of current multi-style ble…