Limitless stability for Graph Convolutional Networks
This work establishes rigorous, novel and widely applicable stability guarantees and transferability bounds for graph convolutional networks -- without reference to any underlying limit object or statistical distribution. Crucially, utilized graph-shift operators (GSOs) are not necessarily assumed t...
Gespeichert in:
1. Verfasser: | |
---|---|
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 |
description | This work establishes rigorous, novel and widely applicable stability
guarantees and transferability bounds for graph convolutional networks --
without reference to any underlying limit object or statistical distribution.
Crucially, utilized graph-shift operators (GSOs) are not necessarily assumed to
be normal, allowing for the treatment of networks on both undirected- and for
the first time also directed graphs. Stability to node-level perturbations is
related to an 'adequate (spectral) covering' property of the filters in each
layer. Stability to edge-level perturbations is related to Lipschitz constants
and newly introduced semi-norms of filters. Results on stability to topological
perturbations are obtained through recently developed mathematical-physics
based tools. As an important and novel example, it is showcased that graph
convolutional networks are stable under graph-coarse-graining procedures
(replacing strongly-connected sub-graphs by single nodes) precisely if the GSO
is the graph Laplacian and filters are regular at infinity. These new
theoretical results are supported by corresponding numerical investigations. |
doi_str_mv | 10.48550/arxiv.2301.11443 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2301_11443</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2301_11443</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-c04bf3f48aedb9f4e39f37ef907cc1965cf84ca0232bafb7af68ac65eb4fcb73</originalsourceid><addsrcrecordid>eNotzrFOwzAUQFEvHVDLBzDhH0hq5zlxMqKoFKQIBtijZ9dPtXDryjaF_j2iMN3t6jB2J0Wt-rYVa0zf_lw3IGQtpVJww9TkD74ElzPPBY0Pvlw4xcS3CU97PsbjOYbP4uMRA39x5Sumj7xiC8KQ3e1_l-ztcfM-PlXT6_Z5fJgq7DRUVihDQKpHtzMDKQcDgXY0CG2tHLrWUq8sigYag2Q0Utej7VpnFFmjYcnu_65X9XxK_oDpMv_q56sefgDeqUEo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Limitless stability for Graph Convolutional Networks</title><source>arXiv.org</source><creator>Koke, Christian</creator><creatorcontrib>Koke, Christian</creatorcontrib><description>This work establishes rigorous, novel and widely applicable stability
guarantees and transferability bounds for graph convolutional networks --
without reference to any underlying limit object or statistical distribution.
Crucially, utilized graph-shift operators (GSOs) are not necessarily assumed to
be normal, allowing for the treatment of networks on both undirected- and for
the first time also directed graphs. Stability to node-level perturbations is
related to an 'adequate (spectral) covering' property of the filters in each
layer. Stability to edge-level perturbations is related to Lipschitz constants
and newly introduced semi-norms of filters. Results on stability to topological
perturbations are obtained through recently developed mathematical-physics
based tools. As an important and novel example, it is showcased that graph
convolutional networks are stable under graph-coarse-graining procedures
(replacing strongly-connected sub-graphs by single nodes) precisely if the GSO
is the graph Laplacian and filters are regular at infinity. These new
theoretical results are supported by corresponding numerical investigations.</description><identifier>DOI: 10.48550/arxiv.2301.11443</identifier><language>eng</language><subject>Computer Science - Learning ; Mathematics - Functional Analysis</subject><creationdate>2023-01</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/2301.11443$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2301.11443$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Koke, Christian</creatorcontrib><title>Limitless stability for Graph Convolutional Networks</title><description>This work establishes rigorous, novel and widely applicable stability
guarantees and transferability bounds for graph convolutional networks --
without reference to any underlying limit object or statistical distribution.
Crucially, utilized graph-shift operators (GSOs) are not necessarily assumed to
be normal, allowing for the treatment of networks on both undirected- and for
the first time also directed graphs. Stability to node-level perturbations is
related to an 'adequate (spectral) covering' property of the filters in each
layer. Stability to edge-level perturbations is related to Lipschitz constants
and newly introduced semi-norms of filters. Results on stability to topological
perturbations are obtained through recently developed mathematical-physics
based tools. As an important and novel example, it is showcased that graph
convolutional networks are stable under graph-coarse-graining procedures
(replacing strongly-connected sub-graphs by single nodes) precisely if the GSO
is the graph Laplacian and filters are regular at infinity. These new
theoretical results are supported by corresponding numerical investigations.</description><subject>Computer Science - Learning</subject><subject>Mathematics - Functional Analysis</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrFOwzAUQFEvHVDLBzDhH0hq5zlxMqKoFKQIBtijZ9dPtXDryjaF_j2iMN3t6jB2J0Wt-rYVa0zf_lw3IGQtpVJww9TkD74ElzPPBY0Pvlw4xcS3CU97PsbjOYbP4uMRA39x5Sumj7xiC8KQ3e1_l-ztcfM-PlXT6_Z5fJgq7DRUVihDQKpHtzMDKQcDgXY0CG2tHLrWUq8sigYag2Q0Utej7VpnFFmjYcnu_65X9XxK_oDpMv_q56sefgDeqUEo</recordid><startdate>20230126</startdate><enddate>20230126</enddate><creator>Koke, Christian</creator><scope>AKY</scope><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20230126</creationdate><title>Limitless stability for Graph Convolutional Networks</title><author>Koke, Christian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-c04bf3f48aedb9f4e39f37ef907cc1965cf84ca0232bafb7af68ac65eb4fcb73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Mathematics - Functional Analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Koke, Christian</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Koke, Christian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Limitless stability for Graph Convolutional Networks</atitle><date>2023-01-26</date><risdate>2023</risdate><abstract>This work establishes rigorous, novel and widely applicable stability
guarantees and transferability bounds for graph convolutional networks --
without reference to any underlying limit object or statistical distribution.
Crucially, utilized graph-shift operators (GSOs) are not necessarily assumed to
be normal, allowing for the treatment of networks on both undirected- and for
the first time also directed graphs. Stability to node-level perturbations is
related to an 'adequate (spectral) covering' property of the filters in each
layer. Stability to edge-level perturbations is related to Lipschitz constants
and newly introduced semi-norms of filters. Results on stability to topological
perturbations are obtained through recently developed mathematical-physics
based tools. As an important and novel example, it is showcased that graph
convolutional networks are stable under graph-coarse-graining procedures
(replacing strongly-connected sub-graphs by single nodes) precisely if the GSO
is the graph Laplacian and filters are regular at infinity. These new
theoretical results are supported by corresponding numerical investigations.</abstract><doi>10.48550/arxiv.2301.11443</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2301.11443 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2301_11443 |
source | arXiv.org |
subjects | Computer Science - Learning Mathematics - Functional Analysis |
title | Limitless stability for Graph Convolutional Networks |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T14%3A01%3A07IST&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=Limitless%20stability%20for%20Graph%20Convolutional%20Networks&rft.au=Koke,%20Christian&rft.date=2023-01-26&rft_id=info:doi/10.48550/arxiv.2301.11443&rft_dat=%3Carxiv_GOX%3E2301_11443%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 |