Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders

Reyhan Kevser Keser, Indrit Nallbani, Nurullah Calik, Aydin Ayanzadeh, Behcet Ugur Tgreyin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

Graphs are usually represented by high dimensional data. Hence, graph embedding is an essential task, which aims to represent a graph in a lower dimension while protecting the original graph's properties. In this paper, we propose a novel graph embedding method called Residual Variational Graph Autoencoder (RVGAE), which boosts variational graph autoencoder's performance utilizing residual connections. Our method's performance is evaluated on the link prediction task. The results demonstrate that our model can achieve better results than graph convolutional neural network (GCN) and variational graph autoencoder (VGAE).

Original languageEnglish
Title of host publication2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728172064
DOIs
Publication statusPublished - 5 Oct 2020
Event28th Signal Processing and Communications Applications Conference, SIU 2020 - Gaziantep, Turkey
Duration: 5 Oct 20207 Oct 2020

Publication series

Name2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

Conference

Conference28th Signal Processing and Communications Applications Conference, SIU 2020
Country/TerritoryTurkey
CityGaziantep
Period5/10/207/10/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Funding

This work is supported in part by Istanbul Technical University (ITU) Vodafone Future Lab under Project No. ITUVF20180901P04.

FundersFunder number
İTÜ Vodafone Future LabITUVF20180901P04
Istanbul Teknik Üniversitesi

    Keywords

    • Graph Embedding
    • Residual Learning
    • Variational Graph Autoen-coders

    Fingerprint

    Dive into the research topics of 'Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders'. Together they form a unique fingerprint.

    Cite this