3 papers
cs.LG2026
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Brown Zaz, Mar Gonzà lez I CatalÃ, Ferran Hernandez Caralt +2
In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on a…
cs.LG2026
On the Necessity of Learnable Sheaf Laplacians
Ferran Hernandez Caralt, Mar Gonzà lez i CatalÃ, Adrián Bazaga +1
Sheaf Neural Networks (SNNs) were introduced as an extension of Graph Convolutional Networks to address oversmoothing on heterophilous graphs by attaching a sheaf to the input grap…
cs.LG2024
Joint Diffusion Processes as an Inductive Bias in Sheaf Neural Networks
Ferran Hernandez Caralt, Guillermo Bernárdez Gil, Iulia Duta +2
Sheaf Neural Networks (SNNs) naturally extend Graph Neural Networks (GNNs) by endowing a cellular sheaf over the graph, equipping nodes and edges with vector spaces and defining li…