3 papers
eess.SP2026
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…
cs.LG2025
Graph Contrastive Learning for Connectome Classification
Martín 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…
cond-mat.stat-mech2024
Spectral Coarse-Graining and Rescaling for Preserving Structural and Dynamical Properties in Graphs
M. Schmidt, F. Caccioli, T. Aste
We introduce a graph renormalization procedure based on the coarse-grained Laplacian, which generates reduced-complexity representations for characteristic scales identified throug…