{"id":"https://openalex.org/W4323521127","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10051821","title":"Learning Stable Graph Neural Networks via Spectral Regularization","display_name":"Learning Stable Graph Neural Networks via Spectral Regularization","publication_year":2022,"publication_date":"2022-10-31","ids":{"openalex":"https://openalex.org/W4323521127","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10051821"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf56349.2022.10051821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf56349.2022.10051821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088013951","display_name":"Zhan Gao","orcid":"https://orcid.org/0000-0001-7250-7386"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Zhan Gao","raw_affiliation_strings":["Delft University of Technology,Department of Intelligent Systems,Delft,The Netherlands","Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Department of Intelligent Systems,Delft,The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060836778","display_name":"Elvin Isufi","orcid":"https://orcid.org/0000-0002-1919-260X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Elvin Isufi","raw_affiliation_strings":["Delft University of Technology,Department of Intelligent Systems,Delft,The Netherlands","Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Department of Intelligent Systems,Delft,The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088013951"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.3979,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68381371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"05"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5774667263031006},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.5408843159675598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5251027345657349},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.45840102434158325},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4394320547580719},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4347354769706726},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4196591079235077},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37870097160339355},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.34659767150878906},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33556199073791504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20888125896453857},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1501549482345581}],"concepts":[{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5774667263031006},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5408843159675598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5251027345657349},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.45840102434158325},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4394320547580719},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4347354769706726},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4196591079235077},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37870097160339355},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.34659767150878906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33556199073791504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20888125896453857},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1501549482345581},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf56349.2022.10051821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf56349.2022.10051821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1698699930","https://openalex.org/W1815611020","https://openalex.org/W2100617218","https://openalex.org/W2137243960","https://openalex.org/W2148386842","https://openalex.org/W2219888463","https://openalex.org/W2885647718","https://openalex.org/W2907492528","https://openalex.org/W2943959761","https://openalex.org/W2966121357","https://openalex.org/W3015591965","https://openalex.org/W3049694790","https://openalex.org/W3095521706","https://openalex.org/W3123684968","https://openalex.org/W3146562665","https://openalex.org/W3160800226","https://openalex.org/W3161893952","https://openalex.org/W3166798139","https://openalex.org/W3175037169","https://openalex.org/W3176675329","https://openalex.org/W3200504467","https://openalex.org/W3202619879","https://openalex.org/W4200631149","https://openalex.org/W4212835176","https://openalex.org/W6760725535","https://openalex.org/W6766750229","https://openalex.org/W6796082418","https://openalex.org/W6805544931"],"related_works":["https://openalex.org/W2165749285","https://openalex.org/W2474979212","https://openalex.org/W2562455930","https://openalex.org/W2001036795","https://openalex.org/W2154748900","https://openalex.org/W3093811938","https://openalex.org/W4390092784","https://openalex.org/W127450631","https://openalex.org/W2062626603","https://openalex.org/W2062690431"],"abstract_inverted_index":{"Stability":[0],"of":[1,62,140],"graph":[2,11,27,45,54,141,149,177],"neural":[3,28],"networks":[4],"(GNNs)":[5],"characterizes":[6],"how":[7],"GNNs":[8],"react":[9],"to":[10,71,78,101,135,144],"perturbations":[12],"and":[13,75,95,116,143,156,162],"provides":[14],"guarantees":[15],"for":[16],"architecture":[17,35,107],"performance":[18,169],"in":[19,43],"noisy":[20],"scenarios.":[21],"This":[22],"paper":[23],"develops":[24],"a":[25,167],"self-regularized":[26],"network":[29],"(SR-GNN)":[30],"solution":[31],"that":[32],"improves":[33,105,179],"the":[34,39,44,53,60,63,67,76,80,88,92,97,106,110,113,118,127,130,137,164,171,175,181],"stability":[36,115],"by":[37,90],"regularizing":[38,96],"filter":[40],"frequency":[41,81,98],"responses":[42],"spectral":[46],"domain.":[47],"The":[48,103],"SR-GNN":[49,89,128,165],"considers":[50],"not":[51],"only":[52],"signal":[55,68],"as":[56],"input":[57],"but":[58,178],"also":[59],"eigenvectors":[61,77],"underlying":[64],"graph,":[65],"where":[66],"is":[69],"processed":[70],"generate":[72],"task-relevant":[73],"features":[74],"characterize":[79],"response":[82,99],"at":[83],"each":[84],"layer.":[85],"We":[86,124],"train":[87],"minimizing":[91],"cost":[93],"function":[94],"close":[100],"one.":[102],"former":[104],"performance,":[108],"while":[109],"latter":[111],"tightens":[112],"perturbation":[114],"alleviates":[117],"information":[119],"loss":[120],"through":[121],"multi-layer":[122],"propagation.":[123],"further":[125],"show":[126,163],"preserves":[129],"permutation":[131],"equivariance,":[132],"which":[133],"allows":[134],"explore":[136],"internal":[138],"symmetries":[139],"signals":[142],"exhibit":[145],"transference":[146],"on":[147,174],"similar":[148],"structures.":[150],"Numerical":[151],"results":[152],"with":[153,170],"source":[154],"localization":[155],"movie":[157],"recommendation":[158],"corroborate":[159],"our":[160],"findings":[161],"yields":[166],"comparable":[168],"vanilla":[172],"GNN":[173],"unperturbed":[176],"substantially":[180],"stability.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}