Robuta

https://arxiv.org/abs/2006.08816v6 [2006.08816v6] Signed Graph Metric Learning via Gershgorin Disc Perfect Alignment Abstract page for arXiv paper 2006.08816v6: Signed Graph Metric Learning via Gershgorin Disc Perfect Alignment signed graphmetric learninggershgorin disc2006 https://openreview.net/forum?id=RZveYHgZbu Signed Graph Neural Networks: A Frequency Perspective | OpenReview Graph convolutional networks (GCNs) and its variants are designed for unsigned graphs containing only positive links. Many existing GCNs have been derived from... graph neural networkssignedfrequencyperspectiveopenreview https://openreview.net/forum?id=KUGwmnSdPV3&referrer=%5Bthe%20profile%20of%20Yixuan%20He%5D(%2Fprofile%3Fid%3D~Yixuan_He2) MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian | OpenReview We devise a novel magnetic signed Laplacian for signed directed networks and propose a GNN method based on that. graph neural networkbased on novel https://openreview.net/forum?id=3CcP3VI6LW Nonlinear Laplacians Improve Signed-Directed Graph Learning | OpenReview While signed-directed graphs have been studied using linear Laplacians in the design of graph neural networks, relatively little research has focused on... directed graphnonlinearimprovesignedlearning