Graph Classification with 2D Convolutional Neural Networks

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

Abstract

Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations. Convolutional Neural Networks (CNNs) offer a very appealing alternative, but processing graphs with CNNs is not trivial. To address this challenge, many sophisticated extensions of CNNs have recently been introduced. In this paper, we reverse the problem: rather than proposing yet another graph CNN model, we introduce a novel way to represent graphs as multi-channel image-like structures that allows them to be handled by vanilla 2D CNNs. Experiments reveal that our method is more accurate than state-of-the-art graph kernels and graph CNNs on 4 out of 6 real-world datasets (with and without continuous node attributes), and close elsewhere. Our approach is also preferable to graph kernels in terms of time complexity. Code and data are publicly available (https://github.com/Tixierae/graph_2D_CNN).

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2019
Subtitle of host publicationWorkshop and Special Sessions - 28th International Conference on Artificial Neural Networks, Proceedings
EditorsVera Kurková, Igor V. Tetko, Pavel Karpov, Fabian Theis
PublisherSpringer Verlag
Pages578-593
Number of pages16
ISBN (Print)9783030304928
DOIs
Publication statusPublished - 1 Jan 2019
Event28th International Conference on Artificial Neural Networks: Workshop and Special Sessions, ICANN 2019 - Munich, Germany
Duration: 17 Sept 201919 Sept 2019

Publication series

NameLecture Notes in Computer Science
Volume11731 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference28th International Conference on Artificial Neural Networks: Workshop and Special Sessions, ICANN 2019
Country/TerritoryGermany
CityMunich
Period17/09/1919/09/19

Fingerprint

Dive into the research topics of 'Graph Classification with 2D Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this