AI RESEARCH
Generalization Bounds for Spectral GNNs via Fourier Domain Analysis
arXiv CS.LG
•
ArXi:2604.00918v1 Announce Type: new Spectral graph neural networks learn graph filters, but their behavior with increasing depth and polynomial order is not well understood. We analyze these models in the graph Fourier domain, where each layer becomes an element-wise frequency update, separating the fixed spectrum from trainable parameters and making depth and order explicit.