2 papers
cs.LG2026
A Unified Framework of Hyperbolic Graph Representation Learning Methods
SofÃa Pérez Casulo, Marcelo Fiori, Bernardo Marenco +1
Hyperbolic geometry has emerged as an effective latent space for representing complex networks, owing to its ability to capture hierarchical organization and heterogeneous connecti…
cs.LG2025
LASE: Learned Adjacency Spectral Embeddings
SofÃa Pérez Casulo, Marcelo Fiori, Federico Larroca +1
We put forth a principled design of a neural architecture to learn nodal Adjacency Spectral Embeddings (ASE) from graph inputs. By bringing to bear the gradient descent (GD) method…