How Powerful are Spectral Graph Neural Networks

By Xiyuan Wang, Muhan Zhang. International Conference on Machine Learning, 2022

331 citations recorded by the source corpus.

Spectral Graph Neural Network is a kind of Graph Neural Network (GNN) based on graph signal filters. Some models able to learn arbitrary spectral filters have emerged recently. However, few works analyze the expressive power of spectral GNNs. This paper studies spectral GNNs' expressive power theoretically. We first prove that even spectral GNNs without nonlinearity can produce arbitrary graph signals and give two conditions for reaching universality. They are: 1) no multiple eigenvalues of graph Laplacian, and 2) no missing frequency components in node features. We also establish a connection between the expressive power of spectral GNNs and Graph Isomorphism (GI) testing, the latter of which is often used to characterize spatial GNNs' expressive power. Moreover, we study the difference in empirical performance among different spectral GNNs with the same expressive power from an optimization perspective, and motivate the use of an orthogonal basis whose weight function corresponds to the graph signal density in the spectrum. Inspired by the analysis, we propose JacobiConv, which uses Jacobi basis due to its orthogonality and flexibility to adapt to a wide range of weight functions. JacobiConv deserts nonlinearity while outperforming all baselines on both synthetic and real-world datasets.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/641828b8ca714a0f70ccdac17d7e9dff485877c2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Artem Babenko
  2. Michael Diskin
  3. Denis Kuznedelev
  4. Oleg Platonov
  5. Liudmila Prokhorenkova
  6. Daniel Cohen-Or
  7. Victor S. Lempitsky

Citations in the corpus