Semi-Supervised Classification with Graph Convolutional Networks

09/09/2016
by   Thomas Kipf, et al.
0

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/21/2019

Spectral-based Graph Convolutional Network for Directed Graphs

Graph convolutional networks(GCNs) have become the most popular approach...
research
02/26/2020

Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes

Graph convolutional neural networks (GCNs) have recently demonstrated pr...
research
10/24/2019

DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters

We propose a novel spectral convolutional neural network (CNN) model on ...
research
07/23/2020

Grale: Designing Networks for Graph Learning

How can we find the right graph for semi-supervised learning? In real wo...
research
01/31/2023

Semi-Supervised Classification with Graph Convolutional Kernel Machines

We present a deep Graph Convolutional Kernel Machine (GCKM) for semi-sup...
research
08/03/2021

Spectral Graph Convolutional Networks With Lifting-based Adaptive Graph Wavelets

Spectral graph convolutional networks (SGCNs) have been attracting incre...
research
01/31/2021

Infant Cry Classification with Graph Convolutional Networks

We propose an approach of graph convolutional networks for robust infant...

Please sign up or login with your details

Forgot password? Click here to reset