4 papers
Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion
Cristina López Amado, Tassilo Schwarz, Yu Tian +1
Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain limited by oversmoothing and poor performance on heterophilic graphs. To…
Global Synchronization in Matrix-Weighted Networks
Anna Gallo, Yu Tian, Renaud Lambiotte +1
Synchronization phenomena in complex systems are fundamental to understanding collective behavior across disciplines. While classical approaches model such systems by using scalar-…
Dirac-Equation Signal Processing: Physics Boosts Topological Machine Learning
Runyue Wang, Yu Tian, Pietro Liò +1
Topological signals are variables or features associated with both nodes and edges of a network. Recently, in the context of Topological Machine Learning, great attention has been…
Matrix-weighted networks for modeling multidimensional dynamics
Yu Tian, Sadamori Kojaku, Hiroki Sayama +1
Networks are powerful tools for modeling interactions in complex systems. While traditional networks use scalar edge weights, many real-world systems involve multidimensional inter…