{"id":"https://openalex.org/W2963272802","doi":"https://doi.org/10.1145/3292500.3330956","title":"Stability and Generalization of Graph Convolutional Neural Networks","display_name":"Stability and Generalization of Graph Convolutional Neural Networks","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963272802","doi":"https://doi.org/10.1145/3292500.3330956","mag":"2963272802"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330956","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330956","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023506097","display_name":"Saurabh Verma","orcid":"https://orcid.org/0000-0003-1489-1871"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saurabh Verma","raw_affiliation_strings":["University of Minnesota Twin Cities, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota Twin Cities, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622097","display_name":"Zhi-Li Zhang","orcid":"https://orcid.org/0000-0001-8584-2319"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi-Li Zhang","raw_affiliation_strings":["University of Minnesota Twin Cities, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota Twin Cities, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023506097"],"corresponding_institution_ids":["https://openalex.org/I130238516","https://openalex.org/I4210101327"],"apc_list":null,"apc_paid":null,"fwci":7.8034,"has_fulltext":true,"cited_by_count":97,"citation_normalized_percentile":{"value":0.97829802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1539","last_page":"1548"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.991100013256073,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9721999764442444,"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/generalization","display_name":"Generalization","score":0.7267573475837708},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6033481359481812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5971867442131042},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5733464956283569},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5136944055557251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4414249062538147},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4198405146598816},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3352010250091553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3204328417778015},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.290947824716568}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7267573475837708},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6033481359481812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5971867442131042},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5733464956283569},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5136944055557251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4414249062538147},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4198405146598816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3352010250091553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3204328417778015},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.290947824716568},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330956","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330956","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330956","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2542344690","display_name":null,"funder_award_id":"1-14-1-0040","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G3148878664","display_name":null,"funder_award_id":"1618339,1617729,1814322","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3205956764","display_name":null,"funder_award_id":"HDTRA1-14-1-0040","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G3596065300","display_name":null,"funder_award_id":"CNS183677","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4461666600","display_name":null,"funder_award_id":"814322","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6541015203","display_name":null,"funder_award_id":"HDTRA1","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G8197787664","display_name":"NeTS: Small: Exerting Logically Centralized Control over Legacy Switches via Incremental SDN Deployment","funder_award_id":"1618339","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8392134187","display_name":null,"funder_award_id":"CNS 1814322","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G966124792","display_name":"NeTS: Small: Collaborative Research: Lightweight Adaptive Algorithms for Network Optimization at Scale towards Emerging Services","funder_award_id":"1814322","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963272802.pdf","grobid_xml":"https://content.openalex.org/works/W2963272802.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1487691575","https://openalex.org/W1534694010","https://openalex.org/W1988318506","https://openalex.org/W2029450386","https://openalex.org/W2101491865","https://openalex.org/W2126523478","https://openalex.org/W2131542408","https://openalex.org/W2139338362","https://openalex.org/W2141088152","https://openalex.org/W2141473882","https://openalex.org/W2144064004","https://openalex.org/W2154952480","https://openalex.org/W2162341153","https://openalex.org/W2171710336","https://openalex.org/W2290854557","https://openalex.org/W2406128552","https://openalex.org/W2468907370","https://openalex.org/W2513671774","https://openalex.org/W2594083602","https://openalex.org/W2604314403","https://openalex.org/W2624431344","https://openalex.org/W2776622059","https://openalex.org/W2899922526","https://openalex.org/W2902515237","https://openalex.org/W2950191616","https://openalex.org/W2962742960","https://openalex.org/W2963739978","https://openalex.org/W2963984147","https://openalex.org/W2978348252","https://openalex.org/W3003419118","https://openalex.org/W3005141333","https://openalex.org/W4212944343","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W4293226380","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2080152487","https://openalex.org/W2239445980","https://openalex.org/W2995553446","https://openalex.org/W2381411913"],"abstract_inverted_index":{"Inspired":[0],"by":[1,68],"convolutional":[2,11],"neural":[3,12],"networks":[4,13],"on":[5,22,30,138,159,189],"1D":[6],"and":[7,25,76,157,164,196],"2D":[8],"data,":[9,24],"graph":[10,23,84,107,131,145,162,190],"(GCNNs)":[14],"have":[15,26],"been":[16],"developed":[17],"for":[18,200],"various":[19,160],"learning":[20,85,191],"tasks":[21],"shown":[27],"superior":[28],"performance":[29],"real-world":[31,161],"datasets.":[32],"Despite":[33],"their":[34,48,78],"success,":[35],"there":[36],"is":[37],"a":[38,56,61,82,96,193],"dearth":[39],"of":[40,43,65,72,95,105,129,141,178],"theoretical":[41,63,173],"explorations":[42],"GCNN":[44,66,74,97,201],"models":[45,67,75],"such":[46],"as":[47],"generalization":[49,79,120,155,198],"properties.":[50],"In":[51,87],"this":[52],"paper,":[53],"we":[54,89,181],"take":[55],"first":[57,184],"step":[58],"towards":[59],"developing":[60],"deeper":[62],"understanding":[64],"analyzing":[69],"the":[70,92,101,113,122,130,139,154,167,176,183],"stability":[71,94,115,158,187],"single-layer":[73],"deriving":[77],"guarantees":[80],"in":[81,192],"semi-supervised":[83,194],"setting.":[86],"particular,":[88],"show":[90,165],"that":[91,166],"algorithmic":[93,150],"model":[98],"depends":[99],"upon":[100],"largest":[102,123],"absolute":[103,124],"eigenvalue":[104,125],"its":[106],"convolution":[108,146],"filter.":[109],"Moreover,":[110],"to":[111,117,185],"ensure":[112],"uniform":[114],"needed":[116],"provide":[118],"strong":[119],"guarantees,":[121],"must":[126],"be":[127],"independent":[128],"size.":[132],"Our":[133],"results":[134,169],"shed":[135],"new":[136,142],"insights":[137],"design":[140],"&":[143],"improved":[144],"filters":[147],"with":[148],"guaranteed":[149],"stability.":[151],"We":[152],"evaluate":[153],"gap":[156],"datasets":[163],"empirical":[168],"indeed":[170],"support":[171],"our":[172,179],"findings.":[174],"To":[175],"best":[177],"knowledge,":[180],"are":[182],"study":[186],"bounds":[188,199],"setting":[195],"derive":[197],"models.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}