3 papers
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…
The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
Mar Gonzà lez I CatalÃ, Haitz Sáez de Ocáriz Borde, George D. Montañez +1
Recent work uses entropy-based signals at multiple representation levels to study reasoning in large language models, but the field remains largely empirical. A central unresolved…
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…