On Filter Size in Graph Convolutional Networks

11/23/2018
by   Dinh Van Tran, et al.
0

Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional filters over multi-dimensional tensors. In particular, we derive a simple, efficient and effective way to introduce a hyper-parameter on graph convolutions that influences the filter size, i.e. its receptive field over the considered graph. We show with experimental results on real-world graph datasets that the proposed graph convolutional filter improves the predictive performance of Deep Graph Convolutional Networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/10/2021

Simple Graph Convolutional Networks

Many neural networks for graphs are based on the graph convolution opera...
research
10/08/2021

New Insights into Graph Convolutional Networks using Neural Tangent Kernels

Graph Convolutional Networks (GCNs) have emerged as powerful tools for l...
research
10/14/2021

SoGCN: Second-Order Graph Convolutional Networks

Graph Convolutional Networks (GCN) with multi-hop aggregation is more ex...
research
06/30/2021

Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification

This paper presents new designs of graph convolutional neural networks (...
research
02/19/2019

Simplifying Graph Convolutional Networks

Graph Convolutional Networks (GCNs) and their variants have experienced ...
research
07/04/2018

BayesGrad: Explaining Predictions of Graph Convolutional Networks

Recent advances in graph convolutional networks have significantly impro...
research
11/14/2022

Evaluating Distribution System Reliability with Hyperstructures Graph Convolutional Nets

Nowadays, it is broadly recognized in the power system community that to...

Please sign up or login with your details

Forgot password? Click here to reset