AI RESEARCH
Full-Spectrum Graph Neural Network: Expressive and Scalable
arXiv CS.LG
•
ArXi:2605.05759v1 Announce Type: new It is well established that spectral graph neural networks (GNNs) can universally approximate node signals; however, their expressive power remains bounded by the 1-dimensional Weisfeiler-Lehman test, which is mirrored in their lack of universality for higher-order signals. To go beyond this bound, we propose the Full-Spectrum GNN (FSpecGNN), a second-order generalization of classical spectral GNNs.