Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders

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

doi:10.1109/SIU49456.2020.9302271

Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders

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

Informatics Institute

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 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 language	English
Title of host publication	2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728172064
DOIs	https://doi.org/10.1109/SIU49456.2020.9302271
Publication status	Published - 5 Oct 2020
Event	28th Signal Processing and Communications Applications Conference, SIU 2020 - Gaziantep, Turkey Duration: 5 Oct 2020 → 7 Oct 2020

Publication series

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

Conference

Conference	28th Signal Processing and Communications Applications Conference, SIU 2020
Country/Territory	Turkey
City	Gaziantep
Period	5/10/20 → 7/10/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

Graph Embedding
Residual Learning
Variational Graph Autoen-coders

Access to Document

10.1109/SIU49456.2020.9302271

Cite this

Keser, R. K., Nallbani, I., Calik, N., Ayanzadeh, A., & Tgreyin, B. U. (2020). Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings Article 9302271 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU49456.2020.9302271

Keser, Reyhan Kevser ; Nallbani, Indrit ; Calik, Nurullah et al. / Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders. 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

@inproceedings{8925e44f18194038ac801018ab0b67f5,

title = "Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders",

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).",

keywords = "Graph Embedding, Residual Learning, Variational Graph Autoen-coders",

author = "Keser, {Reyhan Kevser} and Indrit Nallbani and Nurullah Calik and Aydin Ayanzadeh and Tgreyin, {Behcet Ugur}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 28th Signal Processing and Communications Applications Conference, SIU 2020 ; Conference date: 05-10-2020 Through 07-10-2020",

year = "2020",

month = oct,

day = "5",

doi = "10.1109/SIU49456.2020.9302271",

language = "English",

series = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

address = "United States",

}

Keser, RK, Nallbani, I, Calik, N, Ayanzadeh, A & Tgreyin, BU 2020, Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders. in 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings., 9302271, 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 28th Signal Processing and Communications Applications Conference, SIU 2020, Gaziantep, Turkey, 5/10/20. https://doi.org/10.1109/SIU49456.2020.9302271

Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders. / Keser, Reyhan Kevser; Nallbani, Indrit; Calik, Nurullah et al.
2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9302271 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders

AU - Keser, Reyhan Kevser

AU - Nallbani, Indrit

AU - Calik, Nurullah

AU - Ayanzadeh, Aydin

AU - Tgreyin, Behcet Ugur

PY - 2020/10/5

Y1 - 2020/10/5

N2 - 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).

AB - 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).

KW - Graph Embedding

KW - Residual Learning

KW - Variational Graph Autoen-coders

UR - http://www.scopus.com/inward/record.url?scp=85100302526&partnerID=8YFLogxK

U2 - 10.1109/SIU49456.2020.9302271

DO - 10.1109/SIU49456.2020.9302271

M3 - Conference contribution

AN - SCOPUS:85100302526

T3 - 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 28th Signal Processing and Communications Applications Conference, SIU 2020

Y2 - 5 October 2020 through 7 October 2020

ER -

Keser RK, Nallbani I, Calik N, Ayanzadeh A, Tgreyin BU. Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9302271. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). doi: 10.1109/SIU49456.2020.9302271

Graph Embedding for Link Prediction Using Residual Variational Graph Autoencoders

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this