A Simple Spectral Failure Mode for Graph Convolutional Networks

10/25/2020
by   Carey E. Priebe, et al.
2

We present a simple generative model in which spectral graph embedding for subsequent inference succeeds whereas unsupervised graph convolutional networks (GCN) fail. The geometrical insight is that the GCN is unable to look beyond the first non-informative spectral dimension.

READ FULL TEXT
research
06/05/2019

Variational Spectral Graph Convolutional Networks

We propose a Bayesian approach to spectral graph convolutional networks ...
research
04/12/2022

Adaptive Cross-Attention-Driven Spatial-Spectral Graph Convolutional Network for Hyperspectral Image Classification

Recently, graph convolutional networks (GCNs) have been developed to exp...
research
03/12/2018

Probabilistic and Regularized Graph Convolutional Networks

This paper explores the recently proposed Graph Convolutional Network ar...
research
07/01/2020

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

Graph convolutional networks (GCN) have been recently applied to semi-su...
research
07/13/2020

Distributed Graph Convolutional Networks

The aim of this work is to develop a fully-distributed algorithmic frame...
research
02/22/2021

Dissecting the Diffusion Process in Linear Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have attracted more and more attenti...
research
02/22/2023

Random Projection Forest Initialization for Graph Convolutional Networks

Graph convolutional networks (GCNs) were a great step towards extending ...

Please sign up or login with your details

Forgot password? Click here to reset