Search Results for author:
Found 3 papers, 3 papers with code
Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
These spatial-based HGNNs neglect the utilization of spectral graph convolutions, which are the foundation of Graph Convolutional Networks (GCN) on homogeneous graphs.
Ranked #5 on
Node Property Prediction
on ogbn-mag
Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions.
BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
Many representative graph neural networks, e. g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters.
GPR
Node Classification on Non-Homophilic (Heterophilic) Graphs
