Nonlinear Laplacians Improve Signed-Directed Graph Learning
This work introduces a non-linear Laplacian operator specific to signed and directed networks (NLSD) and proposes an efficient spectral GNN framework (NLSD-GNN), which not only integrates signed and directional data effectively but also achieves superior performance across diverse datasets.
Alipanah Parviz, Yuichi Yoshida
· 3 citations