Maximal Independent Sets for Pooling in Graph Neural Networks
Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2023-07 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Stanovic, Stevan Gaüzère, Benoit Brun, Luc |
description | Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2842265317</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2842265317</sourcerecordid><originalsourceid>FETCH-proquest_journals_28422653173</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSw9U2syMxNzFHwzEtJLUgFEnklCsGpJcUKaflFCgH5-TmZeekKmXkK7kWJBRkKfqmlRUDFfqkl5flF2cU8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvBLLfzNTY0NyYOFUATk03lA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2842265317</pqid></control><display><type>article</type><title>Maximal Independent Sets for Pooling in Graph Neural Networks</title><source>Free E- Journals</source><creator>Stanovic, Stevan ; Gaüzère, Benoit ; Brun, Luc</creator><creatorcontrib>Stanovic, Stevan ; Gaüzère, Benoit ; Brun, Luc</creatorcontrib><description>Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Graph neural networks ; Graphs ; Image classification</subject><ispartof>arXiv.org, 2023-07</ispartof><rights>2023. 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><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Stanovic, Stevan</creatorcontrib><creatorcontrib>Gaüzère, Benoit</creatorcontrib><creatorcontrib>Brun, Luc</creatorcontrib><title>Maximal Independent Sets for Pooling in Graph Neural Networks</title><title>arXiv.org</title><description>Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling.</description><subject>Artificial neural networks</subject><subject>Graph neural networks</subject><subject>Graphs</subject><subject>Image classification</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSw9U2syMxNzFHwzEtJLUgFEnklCsGpJcUKaflFCgH5-TmZeekKmXkK7kWJBRkKfqmlRUDFfqkl5flF2cU8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvBLLfzNTY0NyYOFUATk03lA</recordid><startdate>20230724</startdate><enddate>20230724</enddate><creator>Stanovic, Stevan</creator><creator>Gaüzère, Benoit</creator><creator>Brun, Luc</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>20230724</creationdate><title>Maximal Independent Sets for Pooling in Graph Neural Networks</title><author>Stanovic, Stevan ; Gaüzère, Benoit ; Brun, Luc</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28422653173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Graph neural networks</topic><topic>Graphs</topic><topic>Image classification</topic><toplevel>online_resources</toplevel><creatorcontrib>Stanovic, Stevan</creatorcontrib><creatorcontrib>Gaüzère, Benoit</creatorcontrib><creatorcontrib>Brun, Luc</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</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 Database</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>Stanovic, Stevan</au><au>Gaüzère, Benoit</au><au>Brun, Luc</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Maximal Independent Sets for Pooling in Graph Neural Networks</atitle><jtitle>arXiv.org</jtitle><date>2023-07-24</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling.</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, 2023-07 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2842265317 |
source | Free E- Journals |
subjects | Artificial neural networks Graph neural networks Graphs Image classification |
title | Maximal Independent Sets for Pooling in Graph Neural Networks |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T12%3A59%3A34IST&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=Maximal%20Independent%20Sets%20for%20Pooling%20in%20Graph%20Neural%20Networks&rft.jtitle=arXiv.org&rft.au=Stanovic,%20Stevan&rft.date=2023-07-24&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2842265317%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2842265317&rft_id=info:pmid/&rfr_iscdi=true |