{"id":"https://openalex.org/W4390647534","doi":"https://doi.org/10.48550/arxiv.2401.02143","title":"Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions","display_name":"Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions","publication_year":2024,"publication_date":"2024-01-04","ids":{"openalex":"https://openalex.org/W4390647534","doi":"https://doi.org/10.48550/arxiv.2401.02143"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.02143","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02143","pdf_url":"https://arxiv.org/pdf/2401.02143","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.02143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014600496","display_name":"Cheng\u2013Te Li","orcid":"https://orcid.org/0000-0001-7995-4787"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Cheng-Te","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023750828","display_name":"Yu\u2010Che Tsai","orcid":"https://orcid.org/0000-0002-5947-5823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsai, Yu-Che","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109233310","display_name":"Chih-Yao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Chih-Yao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016099158","display_name":"Jay Chiehen Liao","orcid":"https://orcid.org/0000-0002-1759-4971"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Jay Chiehen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014600496"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9993000030517578,"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":0.9993000030517578,"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/T11719","display_name":"Data Quality and Management","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9740999937057495,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7293400168418884},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5782793164253235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5150372982025146},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5030972361564636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5010473728179932},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4397377371788025},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4149141311645508},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14224061369895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293400168418884},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5782793164253235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5150372982025146},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5030972361564636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5010473728179932},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4397377371788025},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4149141311645508},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14224061369895935},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.02143","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02143","pdf_url":"https://arxiv.org/pdf/2401.02143","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.02143","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.02143","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.02143","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02143","pdf_url":"https://arxiv.org/pdf/2401.02143","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390647534.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W4230611425","https://openalex.org/W2731899572","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W4383066092","https://openalex.org/W3215138031","https://openalex.org/W2804383999","https://openalex.org/W4380075502"],"abstract_inverted_index":{"In":[0,142],"this":[1,230],"survey,":[2],"we":[3,189],"dive":[4],"into":[5,108,121],"Tabular":[6],"Data":[7],"Learning":[8],"(TDL)":[9],"using":[10],"Graph":[11],"Neural":[12],"Networks":[13],"(GNNs),":[14],"a":[15,39,88,105,127,178,208,215],"domain":[16],"where":[17],"deep":[18,43],"learning-based":[19],"approaches":[20],"have":[21,75],"increasingly":[22],"shown":[23],"superior":[24],"performance":[25],"in":[26,42,95,202,221,229],"both":[27],"classification":[28],"and":[29,55,67,79,97,112,135,186,193,212,224],"regression":[30],"tasks":[31,155],"compared":[32],"to":[33,63,156,171,199],"traditional":[34],"methods.":[35,141],"The":[36],"survey":[37,86,145,205],"highlights":[38],"critical":[40,164],"gap":[41],"neural":[44],"TDL":[45,83,101,117,140,223],"methods:":[46],"the":[47,92,109,144,151,158,172,191],"underrepresentation":[48],"of":[49,72,91,115,153,160,166,175,180,218],"latent":[50],"correlations":[51],"among":[52],"data":[53],"instances":[54],"feature":[56],"values.":[57],"GNNs,":[58],"with":[59],"their":[60,122,184],"innate":[61],"capability":[62],"model":[64],"intricate":[65],"relationships":[66],"interactions":[68],"between":[69],"diverse":[70],"elements":[71],"tabular":[73],"data,":[74],"garnered":[76],"significant":[77],"interest":[78],"application":[80,174],"across":[81,177],"various":[82,147],"domains.":[84],"Our":[85],"provides":[87],"systematic":[89],"review":[90],"methods":[93],"involved":[94],"designing":[96],"implementing":[98],"GNNs":[99,176],"for":[100,210],"(GNN4TDL).":[102],"It":[103],"encompasses":[104],"detailed":[106],"investigation":[107],"foundational":[110],"aspects":[111],"an":[113],"overview":[114],"GNN-based":[116,139],"methods,":[118],"offering":[119,214],"insights":[120],"evolving":[123],"landscape.":[124],"We":[125],"present":[126],"comprehensive":[128],"taxonomy":[129],"focused":[130],"on":[131],"constructing":[132],"graph":[133],"structures":[134],"representation":[136],"learning":[137],"within":[138],"addition,":[143],"examines":[146],"training":[148],"plans,":[149],"emphasizing":[150],"integration":[152],"auxiliary":[154],"enhance":[157],"effectiveness":[159],"instance":[161],"representations.":[162],"A":[163],"part":[165],"our":[167],"discussion":[168],"is":[169],"dedicated":[170],"practical":[173],"spectrum":[179],"GNN4TDL":[181],"scenarios,":[182],"demonstrating":[183],"versatility":[185],"impact.":[187],"Lastly,":[188],"discuss":[190],"limitations":[192],"propose":[194],"future":[195,227],"research":[196],"directions,":[197],"aiming":[198],"spur":[200],"advancements":[201],"GNN4TDL.":[203],"This":[204],"serves":[206],"as":[207],"resource":[209],"researchers":[211],"practitioners,":[213],"thorough":[216],"understanding":[217],"GNNs'":[219],"role":[220],"revolutionizing":[222],"pointing":[225],"towards":[226],"innovations":[228],"promising":[231],"area.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-01-10T00:00:00"}