{"id":"https://openalex.org/W4321022077","doi":"https://doi.org/10.1109/access.2023.3246128","title":"Hierarchical Model Selection for Graph Neural Networks","display_name":"Hierarchical Model Selection for Graph Neural Networks","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321022077","doi":"https://doi.org/10.1109/access.2023.3246128"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3246128","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3246128","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047858.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047858.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019144380","display_name":"Yuga Oishi","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuga Oishi","raw_affiliation_strings":["Department of Computer and Network Engineering, Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3878-5830","affiliations":[{"raw_affiliation_string":"Department of Computer and Network Engineering, Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037354785","display_name":"Ken Kaneiwa","orcid":"https://orcid.org/0000-0001-8519-3865"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ken Kaneiwa","raw_affiliation_strings":["Department of Computer and Network Engineering, Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8519-3865","affiliations":[{"raw_affiliation_string":"Department of Computer and Network Engineering, Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01312887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"16974","last_page":"16983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":1.0,"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":1.0,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10028","display_name":"Topic Modeling","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7509607076644897},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5290837287902832},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45577362179756165},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4152945876121521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39068377017974854},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32971876859664917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509607076644897},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5290837287902832},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45577362179756165},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4152945876121521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39068377017974854},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32971876859664917}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3246128","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3246128","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047858.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:15756bfb50f44e03aab45802674dd665","is_oa":true,"landing_page_url":"https://doaj.org/article/15756bfb50f44e03aab45802674dd665","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 16974-16983 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3246128","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3246128","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10047858.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6047228005","display_name":"A Method of Reasoning and Learning for Various Data on the Semantic Web","funder_award_id":"18K11547","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321022077.pdf","grobid_xml":"https://content.openalex.org/works/W4321022077.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1630959083","https://openalex.org/W2153959628","https://openalex.org/W2962756421","https://openalex.org/W3005104128","https://openalex.org/W3011667710","https://openalex.org/W3090999459","https://openalex.org/W3128443161","https://openalex.org/W3152626252","https://openalex.org/W3217574365","https://openalex.org/W4221162328","https://openalex.org/W4233045210","https://openalex.org/W6602764823","https://openalex.org/W6631190155","https://openalex.org/W6726873649","https://openalex.org/W6745537798","https://openalex.org/W6752110883","https://openalex.org/W6754929296","https://openalex.org/W6755863455","https://openalex.org/W6760001035","https://openalex.org/W6771621015","https://openalex.org/W6771932116","https://openalex.org/W6773781011","https://openalex.org/W6779961489","https://openalex.org/W6784977419","https://openalex.org/W6810144495","https://openalex.org/W6849755372"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W3017188156","https://openalex.org/W2322875716","https://openalex.org/W2391251536","https://openalex.org/W2383516975","https://openalex.org/W2374878784","https://openalex.org/W2147679489"],"abstract_inverted_index":{"Node":[0],"classification":[1,64,153],"on":[2,36,74,133,151],"graph":[3,14,30,47,75,115,158],"data":[4,48,76],"is":[5,67],"a":[6,78,87,95],"major":[7],"problem":[8,88],"in":[9,49,61],"machine":[10],"learning,":[11],"and":[12,27,82,121],"various":[13,155],"neural":[15],"networks":[16,32],"(GNNs)":[17],"have":[18],"been":[19],"proposed.":[20],"Variants":[21],"of":[22,39,111,157],"GNNs":[23,60],"such":[24],"as":[25,125],"H2GCN":[26,69],"CPF":[28,83],"outperform":[29],"convolutional":[31],"(GCNs)":[33],"by":[34,145],"improving":[35],"the":[37,40,62,109,129,137,142],"weaknesses":[38],"traditional":[41],"GNN.":[42],"However,":[43],"there":[44],"are":[45],"some":[46],"which":[50],"these":[51],"GNN":[52,105],"variants":[53],"fail":[54],"to":[55,86,107,127],"perform":[56],"well":[57],"than":[58],"other":[59],"node":[63,152],"task.":[65],"This":[66],"because":[68],"has":[70],"similar":[71],"feature":[72],"values":[73],"with":[77,89],"high":[79,149],"average":[80,119],"degree,":[81],"gives":[84],"rise":[85],"label-propagation":[90],"suitability.":[91],"Accordingly,":[92],"we":[93,139],"propose":[94],"hierarchical":[96],"model":[97,106,131,143],"selection":[98],"framework":[99],"(HMSF)":[100],"that":[101,141],"selects":[102],"an":[103],"appropriate":[104],"predict":[108],"class":[110],"nodes":[112],"for":[113,154],"each":[114],"data.":[116,159],"HMSF":[117,147],"uses":[118],"degree":[120],"edge":[122],"homophily":[123],"ratio":[124],"indicators":[126],"decide":[128],"useful":[130],"based":[132],"our":[134,146],"analyses.":[135],"In":[136],"experiment,":[138],"show":[140],"selected":[144],"achieves":[148],"performance":[150],"types":[156]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}