Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited

02/04/2022
by   Mingguo He, et al.
0

Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral convolution using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two Chebyshev polynomials while still outperforming it on real-world datasets. GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral convolution. Such conclusions are counter-intuitive in the field of approximation theory, where it is established that the Chebyshev polynomial achieves the optimum convergent rate for approximating a function. In this paper, we revisit the problem of approximating the spectral convolution with Chebyshev polynomials. We show that ChebNet's inferior performance is primarily due to illegal coefficients learnt by ChebNet approximating analytic filter functions, which leads to over-fitting. We then propose ChebNetII, a new GNN model based on Chebyshev interpolation, which enhances the original Chebyshev polynomial approximation while reducing the Runge phenomena. We conducted an extensive experimental study to demonstrate that ChebNetII can learn arbitrary graph spectrum filters and achieve superior performance in both full- and semi-supervised node classification tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/21/2021

BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

Many representative graph neural networks, e.g., GPR-GNN and ChebyNet, a...
research
08/30/2018

Rational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operator

For node level graph encoding, a recent important state-of-art method is...
research
03/24/2023

LONGNN: Spectral GNNs with Learnable Orthonormal Basis

In recent years, a plethora of spectral graph neural networks (GNN) meth...
research
05/31/2023

Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popu...
research
06/22/2020

Connecting Graph Convolutional Networks and Graph-Regularized PCA

Graph convolution operator of the GCN model is originally motivated from...
research
11/08/2020

Fourier-based and Rational Graph Filters for Spectral Processing

Data are represented as graphs in a wide range of applications, such as ...
research
02/24/2023

Graph Neural Networks with Learnable and Optimal Polynomial Bases

Polynomial filters, a kind of Graph Neural Networks, typically use a pre...

Please sign up or login with your details

Forgot password? Click here to reset