ResolvNet: A Graph Convolutional Network with multi-scale Consistency

It is by now a well known fact in the graph learning community that the presence of bottlenecks severely limits the ability of graph neural networks to propagate information over long distances. What so far has not been appreciated is that, counter-intuitively, also the presence of strongly connecte...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Koke, Christian, Saroha, Abhishek, Shen, Yuesong, Eisenberger, Marvin, Cremers, Daniel
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Koke, Christian
Saroha, Abhishek
Shen, Yuesong
Eisenberger, Marvin
Cremers, Daniel
description It is by now a well known fact in the graph learning community that the presence of bottlenecks severely limits the ability of graph neural networks to propagate information over long distances. What so far has not been appreciated is that, counter-intuitively, also the presence of strongly connected sub-graphs may severely restrict information flow in common architectures. Motivated by this observation, we introduce the concept of multi-scale consistency. At the node level this concept refers to the retention of a connected propagation graph even if connectivity varies over a given graph. At the graph-level, multi-scale consistency refers to the fact that distinct graphs describing the same object at different resolutions should be assigned similar feature vectors. As we show, both properties are not satisfied by poular graph neural network architectures. To remedy these shortcomings, we introduce ResolvNet, a flexible graph neural network based on the mathematical concept of resolvents. We rigorously establish its multi-scale consistency theoretically and verify it in extensive experiments on real world data: Here networks based on this ResolvNet architecture prove expressive; out-performing baselines significantly on many tasks; in- and outside the multi-scale setting.
doi_str_mv 10.48550/arxiv.2310.00431
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2310_00431</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2310_00431</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-5e48d28d70040b2e1b651003ce24a8e1323f11604e273c63b9b55864c22a7b553</originalsourceid><addsrcrecordid>eNotj81OAjEUhbtxYdAHYGVfYLD_U92RCaIJ0cSwn9wpl9BYpqQtg7y9A7g6J-ec3JuPkClnM2W1Zs-Qfv0wE3IMGFOS35PFN-YYhk8sr3ROlwkOO9rEfojhWHzsIdCxOsX0Q0--7Oj-GIqvsoOAl1n2uWDvzg_kbgsh4-O_Tsj6bbFu3qvV1_Kjma8qMDWvNCq7EXZTj79ZJ5B3RnPGpEOhwCKXQm45N0yhqKUzsnvptLZGOSGgHq2ckKfb2StHe0h-D-ncXnjaK4_8A1VfRF0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>ResolvNet: A Graph Convolutional Network with multi-scale Consistency</title><source>arXiv.org</source><creator>Koke, Christian ; Saroha, Abhishek ; Shen, Yuesong ; Eisenberger, Marvin ; Cremers, Daniel</creator><creatorcontrib>Koke, Christian ; Saroha, Abhishek ; Shen, Yuesong ; Eisenberger, Marvin ; Cremers, Daniel</creatorcontrib><description>It is by now a well known fact in the graph learning community that the presence of bottlenecks severely limits the ability of graph neural networks to propagate information over long distances. What so far has not been appreciated is that, counter-intuitively, also the presence of strongly connected sub-graphs may severely restrict information flow in common architectures. Motivated by this observation, we introduce the concept of multi-scale consistency. At the node level this concept refers to the retention of a connected propagation graph even if connectivity varies over a given graph. At the graph-level, multi-scale consistency refers to the fact that distinct graphs describing the same object at different resolutions should be assigned similar feature vectors. As we show, both properties are not satisfied by poular graph neural network architectures. To remedy these shortcomings, we introduce ResolvNet, a flexible graph neural network based on the mathematical concept of resolvents. We rigorously establish its multi-scale consistency theoretically and verify it in extensive experiments on real world data: Here networks based on this ResolvNet architecture prove expressive; out-performing baselines significantly on many tasks; in- and outside the multi-scale setting.</description><identifier>DOI: 10.48550/arxiv.2310.00431</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2023-09</creationdate><rights>http://creativecommons.org/licenses/by-nc-nd/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2310.00431$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2310.00431$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Koke, Christian</creatorcontrib><creatorcontrib>Saroha, Abhishek</creatorcontrib><creatorcontrib>Shen, Yuesong</creatorcontrib><creatorcontrib>Eisenberger, Marvin</creatorcontrib><creatorcontrib>Cremers, Daniel</creatorcontrib><title>ResolvNet: A Graph Convolutional Network with multi-scale Consistency</title><description>It is by now a well known fact in the graph learning community that the presence of bottlenecks severely limits the ability of graph neural networks to propagate information over long distances. What so far has not been appreciated is that, counter-intuitively, also the presence of strongly connected sub-graphs may severely restrict information flow in common architectures. Motivated by this observation, we introduce the concept of multi-scale consistency. At the node level this concept refers to the retention of a connected propagation graph even if connectivity varies over a given graph. At the graph-level, multi-scale consistency refers to the fact that distinct graphs describing the same object at different resolutions should be assigned similar feature vectors. As we show, both properties are not satisfied by poular graph neural network architectures. To remedy these shortcomings, we introduce ResolvNet, a flexible graph neural network based on the mathematical concept of resolvents. We rigorously establish its multi-scale consistency theoretically and verify it in extensive experiments on real world data: Here networks based on this ResolvNet architecture prove expressive; out-performing baselines significantly on many tasks; in- and outside the multi-scale setting.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81OAjEUhbtxYdAHYGVfYLD_U92RCaIJ0cSwn9wpl9BYpqQtg7y9A7g6J-ec3JuPkClnM2W1Zs-Qfv0wE3IMGFOS35PFN-YYhk8sr3ROlwkOO9rEfojhWHzsIdCxOsX0Q0--7Oj-GIqvsoOAl1n2uWDvzg_kbgsh4-O_Tsj6bbFu3qvV1_Kjma8qMDWvNCq7EXZTj79ZJ5B3RnPGpEOhwCKXQm45N0yhqKUzsnvptLZGOSGgHq2ckKfb2StHe0h-D-ncXnjaK4_8A1VfRF0</recordid><startdate>20230930</startdate><enddate>20230930</enddate><creator>Koke, Christian</creator><creator>Saroha, Abhishek</creator><creator>Shen, Yuesong</creator><creator>Eisenberger, Marvin</creator><creator>Cremers, Daniel</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230930</creationdate><title>ResolvNet: A Graph Convolutional Network with multi-scale Consistency</title><author>Koke, Christian ; Saroha, Abhishek ; Shen, Yuesong ; Eisenberger, Marvin ; Cremers, Daniel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-5e48d28d70040b2e1b651003ce24a8e1323f11604e273c63b9b55864c22a7b553</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Koke, Christian</creatorcontrib><creatorcontrib>Saroha, Abhishek</creatorcontrib><creatorcontrib>Shen, Yuesong</creatorcontrib><creatorcontrib>Eisenberger, Marvin</creatorcontrib><creatorcontrib>Cremers, Daniel</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Koke, Christian</au><au>Saroha, Abhishek</au><au>Shen, Yuesong</au><au>Eisenberger, Marvin</au><au>Cremers, Daniel</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ResolvNet: A Graph Convolutional Network with multi-scale Consistency</atitle><date>2023-09-30</date><risdate>2023</risdate><abstract>It is by now a well known fact in the graph learning community that the presence of bottlenecks severely limits the ability of graph neural networks to propagate information over long distances. What so far has not been appreciated is that, counter-intuitively, also the presence of strongly connected sub-graphs may severely restrict information flow in common architectures. Motivated by this observation, we introduce the concept of multi-scale consistency. At the node level this concept refers to the retention of a connected propagation graph even if connectivity varies over a given graph. At the graph-level, multi-scale consistency refers to the fact that distinct graphs describing the same object at different resolutions should be assigned similar feature vectors. As we show, both properties are not satisfied by poular graph neural network architectures. To remedy these shortcomings, we introduce ResolvNet, a flexible graph neural network based on the mathematical concept of resolvents. We rigorously establish its multi-scale consistency theoretically and verify it in extensive experiments on real world data: Here networks based on this ResolvNet architecture prove expressive; out-performing baselines significantly on many tasks; in- and outside the multi-scale setting.</abstract><doi>10.48550/arxiv.2310.00431</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2310.00431
ispartof
issn
language eng
recordid cdi_arxiv_primary_2310_00431
source arXiv.org
subjects Computer Science - Learning
title ResolvNet: A Graph Convolutional Network with multi-scale Consistency
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T02%3A27%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ResolvNet:%20A%20Graph%20Convolutional%20Network%20with%20multi-scale%20Consistency&rft.au=Koke,%20Christian&rft.date=2023-09-30&rft_id=info:doi/10.48550/arxiv.2310.00431&rft_dat=%3Carxiv_GOX%3E2310_00431%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true