{"id":"https://openalex.org/W2964040729","doi":"https://doi.org/10.48550/arxiv.1907.09495","title":"IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification","display_name":"IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification","publication_year":2019,"publication_date":"2019-07-22","ids":{"openalex":"https://openalex.org/W2964040729","doi":"https://doi.org/10.48550/arxiv.1907.09495","mag":"2964040729"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1907.09495","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.09495","pdf_url":"https://arxiv.org/pdf/1907.09495","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.09495","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076579498","display_name":"Lin Meng","orcid":"https://orcid.org/0000-0003-4351-6923","observed_orcids":["https://orcid.org/0000-0003-4351-6923","https://orcid.org/0000-0001-9787-9936"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462824","display_name":"Jiawei Zhang","orcid":"https://orcid.org/0000-0002-2111-7617","observed_orcids":["https://orcid.org/0000-0002-2111-7617"]},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Jiawei","raw_affiliation_strings":["IFM Lab Florida State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFM Lab Florida State University","institution_ids":["https://openalex.org/I103163165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9336000084877014,"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":0.9336000084877014,"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":0.06350000202655792,"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/T11476","display_name":"Graph theory and applications","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-representation-learning","display_name":"graph representation learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/graph-classification","display_name":"graph classification","score":0.9929999709129333},{"id":"https://openalex.org/keywords/graph-isomorphism","display_name":"graph isomorphism","score":0.8399999737739563},{"id":"https://openalex.org/keywords/graph-matching","display_name":"graph matching","score":0.7160000205039978},{"id":"https://openalex.org/keywords/permutation-matrix","display_name":"permutation matrices","score":0.925000011920929},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.6212851405143738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5883935689926147},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.5391002893447876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5000159740447998},{"id":"https://openalex.org/C61665672","wikidata":"https://www.wikidata.org/wiki/Q303100","display_name":"Graph isomorphism","level":4,"score":0.49333301186561584},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4892823398113251},{"id":"https://openalex.org/C17192189","wikidata":"https://www.wikidata.org/wiki/Q1347059","display_name":"Epigraph","level":2,"score":0.4600925147533417},{"id":"https://openalex.org/C128115575","wikidata":"https://www.wikidata.org/wiki/Q5597083","display_name":"Graph factorization","level":5,"score":0.45333394408226013},{"id":"https://openalex.org/C193435613","wikidata":"https://www.wikidata.org/wiki/Q2997928","display_name":"Connected component","level":2,"score":0.4469887614250183},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.42616838216781616},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4176553189754486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4028451442718506},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.309758722782135},{"id":"https://openalex.org/C22149727","wikidata":"https://www.wikidata.org/wiki/Q7940747","display_name":"Voltage graph","level":4,"score":0.2895910143852234},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.25578707456588745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25044918060302734},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.12835758924484253},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.09827744960784912},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1907.09495","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.09495","pdf_url":"https://arxiv.org/pdf/1907.09495","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2964040729","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1907.09495","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.09495","doi":"https://doi.org/10.48550/arxiv.1907.09495","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.09495","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.09495","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.09495","pdf_url":"https://arxiv.org/pdf/1907.09495","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1127172264","https://openalex.org/W1524882660","https://openalex.org/W1973208002","https://openalex.org/W2037963635","https://openalex.org/W2107410045","https://openalex.org/W2112837588","https://openalex.org/W2113014179","https://openalex.org/W2122255072","https://openalex.org/W2127795553","https://openalex.org/W2145094598","https://openalex.org/W2145388307","https://openalex.org/W2148611932","https://openalex.org/W2170726034","https://openalex.org/W2184957013","https://openalex.org/W2229441104","https://openalex.org/W2240571584","https://openalex.org/W2273249530","https://openalex.org/W2519887557","https://openalex.org/W2558460151","https://openalex.org/W2606780347","https://openalex.org/W2737925311","https://openalex.org/W2741206673","https://openalex.org/W2742812719","https://openalex.org/W2770604839","https://openalex.org/W2788919350","https://openalex.org/W2791126026","https://openalex.org/W2805516822","https://openalex.org/W2809343047","https://openalex.org/W2888799009","https://openalex.org/W2890855364","https://openalex.org/W2898095674","https://openalex.org/W2962711740","https://openalex.org/W2962756421","https://openalex.org/W2962767366","https://openalex.org/W2962995121","https://openalex.org/W2963984147"],"related_works":["https://openalex.org/W3043242689","https://openalex.org/W3156971038","https://openalex.org/W3214502880","https://openalex.org/W2792034376","https://openalex.org/W2788919350","https://openalex.org/W2947148979","https://openalex.org/W3093002101","https://openalex.org/W2809343047","https://openalex.org/W3043761945","https://openalex.org/W2894818806","https://openalex.org/W3211716863","https://openalex.org/W2083792122","https://openalex.org/W3034116706","https://openalex.org/W3095213891","https://openalex.org/W2942223620","https://openalex.org/W2995557627","https://openalex.org/W2737925311","https://openalex.org/W1488211288","https://openalex.org/W2972933289","https://openalex.org/W2991555167"],"abstract_inverted_index":{"Deep":[0],"learning":[1,29],"models":[2,30,59,72],"have":[3],"achieved":[4],"huge":[5],"success":[6],"in":[7,147,164,185],"numerous":[8],"fields,":[9,21],"such":[10,20,71],"as":[11,136,181],"computer":[12],"vision":[13],"and":[14,47,66,109,121,151,208],"natural":[15],"language":[16],"processing.":[17],"However,":[18],"unlike":[19],"it":[22],"is":[23,162],"hard":[24],"to":[25,36,140,167],"apply":[26],"traditional":[27],"deep":[28,58],"on":[31,50,60,191],"the":[32,37,51,55,67,78,94,103,137,142,148,154,165,169,173,182,194,199],"graph":[33,61,95,104,108,116,125,150,210],"data":[34],"due":[35],"'node-orderless'":[38],"property.":[39],"Normally,":[40],"adjacency":[41],"matrices":[42,161],"will":[43],"cast":[44],"an":[45],"artificial":[46],"random":[48],"node-order":[49,80,170],"graphs,":[52],"which":[53,92],"renders":[54],"performance":[56],"of":[57,133,159,201],"classification":[62,122,183,211],"tasks":[63],"extremely":[64],"erratic,":[65],"representations":[68],"learned":[69],"by":[70,97,172],"lack":[73],"clear":[74],"interpretability.":[75],"To":[76],"eliminate":[77],"unnecessary":[79],"constraint,":[81],"we":[82],"propose":[83],"a":[84,131],"novel":[85],"model":[86],"named":[87],"Isomorphic":[88],"Neural":[89],"Network":[90],"(IsoNN),":[91],"learns":[93],"representation":[96],"extracting":[98],"its":[99],"isomorphic":[100,117,126,155],"features":[101],"via":[102],"matching":[105],"between":[106],"input":[107,149],"templates.":[110],"IsoNN":[111],"has":[112],"two":[113],"main":[114],"components:":[115],"feature":[118,127],"extraction":[119,128],"component":[120,129,166,184],"component.":[123],"The":[124],"utilizes":[130],"set":[132,158],"subgraph":[134,144],"templates":[135],"kernel":[138],"variables":[139],"learn":[141],"possible":[143],"patterns":[145],"existing":[146],"then":[152],"computes":[153],"features.":[156],"A":[157],"permutation":[160],"used":[163,180],"break":[168],"brought":[171],"matrix":[174],"representation.":[175],"Three":[176],"fully-connected":[177],"layers":[178],"are":[179,189],"IsoNN.":[186],"Extensive":[187],"experiments":[188],"conducted":[190],"benchmark":[192],"datasets,":[193],"experimental":[195],"results":[196],"can":[197],"demonstrate":[198],"effectiveness":[200],"ISONN,":[202],"especially":[203],"compared":[204],"with":[205],"both":[206],"classic":[207],"state-of-the-art":[209],"methods.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}