Graph generative adversarial network

Graph generative adversarial network

In this report, we briefly explain the building blocks of Generative Adversarial Network (GAN), recent research on generalization of Convolution Neural Network (CNN) to graphs, and experimented on further usage of graph convolution on other types of model. We also proposed a simple method to upsampl...

Full description

Saved in:
Bibliographic Details
Main Author: Tjeng, Stefan Setyadi
Other Authors: Xavier Bresson
Format: Final Year Project
Language:English
Published: 2018
Subjects:
DRNTU::Engineering::Computer science and engineering
Online Access:http://hdl.handle.net/10356/73993
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-73993
record_format dspace
spelling sg-ntu-dr.10356-739932023-03-03T20:26:55Z Graph generative adversarial network Tjeng, Stefan Setyadi Xavier Bresson School of Computer Science and Engineering Centre for Multimedia and Network Technology DRNTU::Engineering::Computer science and engineering In this report, we briefly explain the building blocks of Generative Adversarial Network (GAN), recent research on generalization of Convolution Neural Network (CNN) to graphs, and experimented on further usage of graph convolution on other types of model. We also proposed a simple method to upsample graphs. Experiments include usage of graph convolution on Variational Autoencoder (VAE) and GAN. Comparison of result between traditional and proposed graph VAE are observed showing graph VAE achieving better performance. An experimentation on Graph GAN shows the model is unable to converge. Problem analysis and idea for improvement on graph convolution and upsampling are given. Bachelor of Engineering (Computer Science) 2018-04-23T04:44:11Z 2018-04-23T04:44:11Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/73993 en Nanyang Technological University 21 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Tjeng, Stefan Setyadi
Graph generative adversarial network
description In this report, we briefly explain the building blocks of Generative Adversarial Network (GAN), recent research on generalization of Convolution Neural Network (CNN) to graphs, and experimented on further usage of graph convolution on other types of model. We also proposed a simple method to upsample graphs. Experiments include usage of graph convolution on Variational Autoencoder (VAE) and GAN. Comparison of result between traditional and proposed graph VAE are observed showing graph VAE achieving better performance. An experimentation on Graph GAN shows the model is unable to converge. Problem analysis and idea for improvement on graph convolution and upsampling are given.
author2 Xavier Bresson
author_facet Xavier Bresson
Tjeng, Stefan Setyadi
format Final Year Project
author Tjeng, Stefan Setyadi
author_sort Tjeng, Stefan Setyadi
title Graph generative adversarial network
title_short Graph generative adversarial network
title_full Graph generative adversarial network
title_fullStr Graph generative adversarial network
title_full_unstemmed Graph generative adversarial network
title_sort graph generative adversarial network
publishDate 2018
url http://hdl.handle.net/10356/73993
_version_ 1759857655380180992

Similar Items