AI RESEARCH
Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification
arXiv CS.LG
•
ArXi:2603.19091v1 Announce Type: new Spectral Graph Neural Networks (Spectral GNNs) for node classification promise frequency-domain filtering on graphs, yet rest on flawed foundations. Recent work shows that graph Laplacian eigenvectors do not in general have the key properties of a true Fourier basis, but leaves the empirical success of Spectral GNNs unexplained.