Augmenting graph convolutional neural networks with highpass filters

Ansarizadeh, Fatemeh, Tay, David B, Thiruvady, Dhananjay and Robles-Kelly, Antonio 2021, Augmenting graph convolutional neural networks with highpass filters, in S+SSPR 2021 : Proceedings of the IAPR International Workshops on Structural, Syntactic, and Statistical Pattern Recognition and Statistical Techniques in Pattern Recognition, Springer, Cham, Switzerland, pp. 77-86, doi: 10.1007/978-3-030-73973-7_8.

Attached Files
Name Description MIMEType Size Downloads

Title Augmenting graph convolutional neural networks with highpass filters
Author(s) Ansarizadeh, Fatemeh
Tay, David BORCID iD for Tay, David B orcid.org/0000-0001-5285-7426
Thiruvady, DhananjayORCID iD for Thiruvady, Dhananjay orcid.org/0000-0002-8011-933X
Robles-Kelly, AntonioORCID iD for Robles-Kelly, Antonio orcid.org/0000-0002-2465-5971
Conference name International Association of Pattern Recognition. Workshops (2021 : Online from Italy)
Conference location Online from Italy
Conference dates 2021/01/21 - 2021/01/22
Title of proceedings S+SSPR 2021 : Proceedings of the IAPR International Workshops on Structural, Syntactic, and Statistical Pattern Recognition and Statistical Techniques in Pattern Recognition
Editor(s) Torsello, A
Rossi, L
Pelillo, M
Biggio, B
Robles-Kelly, AntonioORCID iD for Robles-Kelly, Antonio orcid.org/0000-0002-2465-5971
Publication date 2021
Series International Association of Pattern Recognition Workshops
Start page 77
End page 86
Total pages 10
Publisher Springer
Place of publication Cham, Switzerland
Keyword(s) Citation graph
Graph convolutional neural networks
Knowledge graph
Summary In this paper, we propose a graph neural network that employs high-pass filters in the convolutional layers. To do this, we depart from a linear model for the convolutional layer and consider the case of directed graphs. This allows for graph spectral theory and the connections between eigenfunctions over the graph and Fourier analysis to employ graph signal processing to obtain an architecture that “concatenates” low and high-pass filters to process data on a connected graph. This yields a method that is quite general in nature applicable to directed and undirected graphs and with clear links to graph spectral methods, Fourier analysis and graph signal processing. Here, we illustrate the utility of our graph convolutional approach to the classification using citation datasets and knowledge graphs. The results show that our method provides a margin of improvement over the alternative.
ISBN 9783030739720
ISSN 0302-9743
1611-3349
Language eng
DOI 10.1007/978-3-030-73973-7_8
Indigenous content off
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30150056

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 11 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Mon, 19 Apr 2021, 12:24:01 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.