2 code implementations • 31 May 2023 • Mingguo He, Zhewei Wei, Shikun Feng, Zhengjie Huang, Weibin Li, Yu Sun, dianhai yu
Furthermore, these methods cannot learn arbitrary valid heterogeneous graph filters within the spectral domain, which have limited expressiveness.
Ranked #5 on Node Property Prediction on ogbn-mag
1 code implementation • 4 Feb 2022 • Mingguo He, Zhewei Wei, Ji-Rong Wen
GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions.
1 code implementation • NeurIPS 2021 • Mingguo He, Zhewei Wei, Zengfeng Huang, Hongteng Xu
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