Description
ChebNet involves a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs.
Description from: Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Papers Using This Method
From ChebNet to ChebGibbsNet2024-12-02Graph Neural Network, ChebNet, Graph Convolutional Network, and Graph Autoencoder: Tutorial and Survey2024-07-08Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited2022-02-04BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation2021-06-21Comparisons of Graph Neural Networks on Cancer Classification Leveraging a Joint of Phenotypic and Genetic Features2021-01-14Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering2016-06-30