From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation

07/01/2020
by   Han Zhang, et al.
0

Graph convolutional networks (GCN) have been recently applied to semi-supervised classification problems with fewer labeled data and higher-dimensional features. Existing GCNs mostly rely on a first-order Chebyshev approximation of the graph wavelet-kernels. Such a generic propagation model may not always be well suited for the datasets. This work revisits the fundamentals of graph wavelet and explores the utility of spectral wavelet-kernels to signal propagation in the vertex domain. We first derive the conditions for representing the graph wavelet-kernels via vertex propagation. We next propose alternative propagation models for GCN layers based on Taylor expansions. We further analyze the choices of detailed propagation models. We test the proposed Taylor-based GCN (TGCN) in citation networks and 3D point clouds to demonstrate its advantages over traditional GCN methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/25/2020

A Simple Spectral Failure Mode for Graph Convolutional Networks

We present a simple generative model in which spectral graph embedding f...
research
07/21/2019

Spectral-based Graph Convolutional Network for Directed Graphs

Graph convolutional networks(GCNs) have become the most popular approach...
research
10/14/2018

Personalized Embedding Propagation: Combining Neural Networks on Graphs with Personalized PageRank

Neural message passing algorithms for semi-supervised classification on ...
research
08/03/2020

Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs

Graph Convolutional Networks (GCNs) have proven to be successful tools f...
research
02/22/2021

Dissecting the Diffusion Process in Linear Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have attracted more and more attenti...
research
10/14/2021

SoGCN: Second-Order Graph Convolutional Networks

Graph Convolutional Networks (GCN) with multi-hop aggregation is more ex...
research
11/22/2020

Stacked Graph Filter

We study Graph Convolutional Networks (GCN) from the graph signal proces...

Please sign up or login with your details

Forgot password? Click here to reset