4 papers
Stability of Flow Models for Graph Signals
Martin Schmidt, Gonzalo Mateos
Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations. While favorable stability properties…
Weighted Random Dot Product Graphs
Bernardo Marenco, Paola Bermolen, Marcelo Fiori +2
Modeling of intricate relational patterns has become a cornerstone of contemporary statistical research and related data science fields. Networks, represented as graphs, offer a na…
Graph Contrastive Learning for Connectome Classification
MartÃn Schmidt, Sara Silva, Federico Larroca +2
With recent advancements in non-invasive techniques for measuring brain activity, such as magnetic resonance imaging (MRI), the study of structural and functional brain networks th…
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…