Training-free Graph Neural Networks and the Power of Labels as Features

We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-08
Main Author: Sato, Ryoma
Format: Article
Language:English
Subjects:
Graph neural networks
Labels
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 Sato, Ryoma
description We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3049801276</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3049801276</sourcerecordid><originalsourceid>FETCH-proquest_journals_30498012763</originalsourceid><addsrcrecordid>eNqNissKgkAUQIcgSMp_uNBaGGd8tY60RUQL9zLSNTWZsTsz-Pu56ANaHTjnbFggpIyjIhFix0JrR865yHKRpjJgVU1q0IN-RR0hQkVq7uGOntS0wi2G3haUfoLrER5mQQLTwU21OK3eQonKeUJ7YNtOTRbDH_fsWF7q8zWayXw8WteMxpNeUyN5cip4LPJM_nd9AaDbOtk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3049801276</pqid></control><display><type>article</type><title>Training-free Graph Neural Networks and the Power of Labels as Features</title><source>Publicly Available Content (ProQuest)</source><creator>Sato, Ryoma</creator><creatorcontrib>Sato, Ryoma</creatorcontrib><description>We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Graph neural networks ; Labels</subject><ispartof>arXiv.org, 2024-08</ispartof><rights>2024. 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/3049801276?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Sato, Ryoma</creatorcontrib><title>Training-free Graph Neural Networks and the Power of Labels as Features</title><title>arXiv.org</title><description>We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs.</description><subject>Graph neural networks</subject><subject>Labels</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNissKgkAUQIcgSMp_uNBaGGd8tY60RUQL9zLSNTWZsTsz-Pu56ANaHTjnbFggpIyjIhFix0JrR865yHKRpjJgVU1q0IN-RR0hQkVq7uGOntS0wi2G3haUfoLrER5mQQLTwU21OK3eQonKeUJ7YNtOTRbDH_fsWF7q8zWayXw8WteMxpNeUyN5cip4LPJM_nd9AaDbOtk</recordid><startdate>20240815</startdate><enddate>20240815</enddate><creator>Sato, Ryoma</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>20240815</creationdate><title>Training-free Graph Neural Networks and the Power of Labels as Features</title><author>Sato, Ryoma</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30498012763</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Graph neural networks</topic><topic>Labels</topic><toplevel>online_resources</toplevel><creatorcontrib>Sato, Ryoma</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest 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>Sato, Ryoma</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Training-free Graph Neural Networks and the Power of Labels as Features</atitle><jtitle>arXiv.org</jtitle><date>2024-08-15</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>We propose training-free graph neural networks (TFGNNs), which can be used without training and can also be improved with optional training, for transductive node classification. We first advocate labels as features (LaF), which is an admissible but not explored technique. We show that LaF provably enhances the expressive power of graph neural networks. We design TFGNNs based on this analysis. In the experiments, we confirm that TFGNNs outperform existing GNNs in the training-free setting and converge with much fewer training iterations than traditional GNNs.</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, 2024-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_3049801276
source Publicly Available Content (ProQuest)
subjects Graph neural networks
Labels
title Training-free Graph Neural Networks and the Power of Labels as Features
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T22%3A48%3A48IST&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=Training-free%20Graph%20Neural%20Networks%20and%20the%20Power%20of%20Labels%20as%20Features&rft.jtitle=arXiv.org&rft.au=Sato,%20Ryoma&rft.date=2024-08-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3049801276%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_30498012763%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3049801276&rft_id=info:pmid/&rfr_iscdi=true