5 papers
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Antonis Vasileiou, Juan Cervino, Pascal Frossard +7
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine lea…
Root-to-Leaf Path Random Walks, Normalized Hodge Laplacians, and Cheeger Inequalities on Simplicial Complexes
Francesco Viganò, Tolga Birdal, Michael T. Schaub +1
We introduce root-to-leaf path random walks on double covers of graded signed graphs and analyze their behavior in a general setting. Viewing simplicial complexes within this frame…
Grassmanian Interpolation of Low-Pass Graph Filters: Theory and Applications
Anton Savostianov, Michael T. Schaub, Benjamin Stamm
Low-pass graph filters are fundamental for signal processing on graphs and other non-Euclidean domains. However, the computation of such filters for parametric graph families can b…
Efficient Sparsification of Simplicial Complexes via Local Densities of States
Anton Savostianov, Michael T. Schaub, Nicola Guglielmi +1
Simplicial complexes (SCs) have become a popular abstraction for analyzing complex data using tools from topological data analysis or topological signal processing. However, the an…
Convergence of gradient based training for linear Graph Neural Networks
Dhiraj Patel, Anton Savostianov, Michael T. Schaub
Graph Neural Networks (GNNs) are powerful tools for addressing learning problems on graph structures, with a wide range of applications in molecular biology and social networks. Ho…