On Node Features for Graph Neural Networks

Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-11
Main Authors: Duong, Chi Thang, Thanh Dat Hoang, Ha The Hien Dang, Quoc Viet Hung Nguyen, Aberer, Karl
Format: Article
Language:English
Subjects:
Graph neural networks
Graph representations
Graphical representations
Graphs
Learning
Neural networks
Nodes
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Duong, Chi Thang
Thanh Dat Hoang
Ha The Hien Dang
Quoc Viet Hung Nguyen
Aberer, Karl
description Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-attributed graphs. Our experimental results show that the artificial features are highly competitive with real features.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2316665007</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2316665007</sourcerecordid><originalsourceid>FETCH-proquest_journals_23166650073</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQ8s9T8MtPSVVwS00sKS1KLVZIyy9ScC9KLMhQ8EstLUrMAVIl5flF2cU8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvZGxoZmZmamBgbkycKgDEvTA2</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2316665007</pqid></control><display><type>article</type><title>On Node Features for Graph Neural Networks</title><source>Publicly Available Content (ProQuest)</source><creator>Duong, Chi Thang ; Thanh Dat Hoang ; Ha The Hien Dang ; Quoc Viet Hung Nguyen ; Aberer, Karl</creator><creatorcontrib>Duong, Chi Thang ; Thanh Dat Hoang ; Ha The Hien Dang ; Quoc Viet Hung Nguyen ; Aberer, Karl</creatorcontrib><description>Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-attributed graphs. Our experimental results show that the artificial features are highly competitive with real features.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Graph neural networks ; Graph representations ; Graphical representations ; Graphs ; Learning ; Neural networks ; Nodes</subject><ispartof>arXiv.org, 2019-11</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2316665007?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25752,37011,44589</link.rule.ids></links><search><creatorcontrib>Duong, Chi Thang</creatorcontrib><creatorcontrib>Thanh Dat Hoang</creatorcontrib><creatorcontrib>Ha The Hien Dang</creatorcontrib><creatorcontrib>Quoc Viet Hung Nguyen</creatorcontrib><creatorcontrib>Aberer, Karl</creatorcontrib><title>On Node Features for Graph Neural Networks</title><title>arXiv.org</title><description>Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-attributed graphs. Our experimental results show that the artificial features are highly competitive with real features.</description><subject>Graph neural networks</subject><subject>Graph representations</subject><subject>Graphical representations</subject><subject>Graphs</subject><subject>Learning</subject><subject>Neural networks</subject><subject>Nodes</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQ8s9T8MtPSVVwS00sKS1KLVZIyy9ScC9KLMhQ8EstLUrMAVIl5flF2cU8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvZGxoZmZmamBgbkycKgDEvTA2</recordid><startdate>20191120</startdate><enddate>20191120</enddate><creator>Duong, Chi Thang</creator><creator>Thanh Dat Hoang</creator><creator>Ha The Hien Dang</creator><creator>Quoc Viet Hung Nguyen</creator><creator>Aberer, Karl</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20191120</creationdate><title>On Node Features for Graph Neural Networks</title><author>Duong, Chi Thang ; Thanh Dat Hoang ; Ha The Hien Dang ; Quoc Viet Hung Nguyen ; Aberer, Karl</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23166650073</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Graph neural networks</topic><topic>Graph representations</topic><topic>Graphical representations</topic><topic>Graphs</topic><topic>Learning</topic><topic>Neural networks</topic><topic>Nodes</topic><toplevel>online_resources</toplevel><creatorcontrib>Duong, Chi Thang</creatorcontrib><creatorcontrib>Thanh Dat Hoang</creatorcontrib><creatorcontrib>Ha The Hien Dang</creatorcontrib><creatorcontrib>Quoc Viet Hung Nguyen</creatorcontrib><creatorcontrib>Aberer, Karl</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Duong, Chi Thang</au><au>Thanh Dat Hoang</au><au>Ha The Hien Dang</au><au>Quoc Viet Hung Nguyen</au><au>Aberer, Karl</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>On Node Features for Graph Neural Networks</atitle><jtitle>arXiv.org</jtitle><date>2019-11-20</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-attributed graphs. Our experimental results show that the artificial features are highly competitive with real features.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2019-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2316665007
source Publicly Available Content (ProQuest)
subjects Graph neural networks
Graph representations
Graphical representations
Graphs
Learning
Neural networks
Nodes
title On Node Features for Graph Neural Networks
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T02%3A03%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=On%20Node%20Features%20for%20Graph%20Neural%20Networks&rft.jtitle=arXiv.org&rft.au=Duong,%20Chi%20Thang&rft.date=2019-11-20&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2316665007%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_23166650073%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2316665007&rft_id=info:pmid/&rfr_iscdi=true