FSpecGNN generalizes spectral GNNs to a second-order form via node-pair lifting and bivariate spectral filters, matching Local 2-GNN expressivity while universally approximating node-pair signals and admitting scalable low-rank implementations.
The Eleventh International Conference on Learning Representations , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
Learnable magnetic spectral PEs of the form h_θ(A_q)R, computed in Hermitian block Krylov subspaces, are eigenbasis-independent, O(log 1/ε)-approximable for heat–resolvent families, and recover directed structure where symmetrized baselines fail.
citing papers explorer
-
Full-Spectrum Graph Neural Networks: Expressive and Scalable
FSpecGNN generalizes spectral GNNs to a second-order form via node-pair lifting and bivariate spectral filters, matching Local 2-GNN expressivity while universally approximating node-pair signals and admitting scalable low-rank implementations.
-
Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
Learnable magnetic spectral PEs of the form h_θ(A_q)R, computed in Hermitian block Krylov subspaces, are eigenbasis-independent, O(log 1/ε)-approximable for heat–resolvent families, and recover directed structure where symmetrized baselines fail.