{"id":"https://openalex.org/W4415317846","doi":"https://doi.org/10.1145/3774904.3792734","title":"Relational Database Distillation: From Structured Tables to Condensed Graph Data","display_name":"Relational Database Distillation: From Structured Tables to Condensed Graph Data","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W4415317846","doi":"https://doi.org/10.1145/3774904.3792734"},"language":"en","primary_location":{"id":"doi:10.1145/3774904.3792734","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792734","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102153605","display_name":"Xing Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xinyi Gao","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0009-0004-1146-8925","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080086543","display_name":"Jingxi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingxi Zhang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0009-0000-7102-7997","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lijian Chen","orcid":"https://orcid.org/0009-0005-7351-7574"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lijian Chen","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0009-0005-7351-7574","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461265","display_name":"Tong Chen","orcid":"https://orcid.org/0000-0001-7269-146X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tong Chen","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7269-146X","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101414718","display_name":"Lizhen Cui","orcid":"https://orcid.org/0000-0002-8262-8883"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhen Cui","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-8262-8883","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088492734","display_name":"Hongzhi Yin","orcid":"https://orcid.org/0000-0003-1395-261X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongzhi Yin","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1395-261X","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00657875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4919","last_page":"4928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9620000123977661,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9620000123977661,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9115999937057495,"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/relational-database","display_name":"Relational database","score":0.6448000073432922},{"id":"https://openalex.org/keywords/relational-database-management-system","display_name":"Relational database management system","score":0.588699996471405},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5116999745368958},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.38989999890327454},{"id":"https://openalex.org/keywords/relational-model","display_name":"Relational model","score":0.335099995136261},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3325999975204468},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.33009999990463257},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.31769999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408999800682068},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6448000073432922},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.588699996471405},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3555999994277954},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C95916125","wikidata":"https://www.wikidata.org/wiki/Q840540","display_name":"Relational algebra","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C65647387","wikidata":"https://www.wikidata.org/wiki/Q1781706","display_name":"Conjunctive query","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774904.3792734","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792734","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.06980","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06980","pdf_url":"https://arxiv.org/pdf/2510.06980","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.48550/arxiv.2510.06980","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.06980","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":"doi:10.1145/3774904.3792734","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792734","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Relational":[0,119],"databases":[1],"(RDBs)":[2],"underpin":[3],"the":[4,52,82,92,98,116,136,180,201,216],"majority":[5],"of":[6,46,95,101,118],"global":[7],"data":[8,27,166,217],"management":[9],"systems,":[10],"where":[11],"information":[12,148],"is":[13,149],"structured":[14],"into":[15,130],"multiple":[16,207],"interdependent":[17],"tables.":[18,107],"In":[19],"social":[20,47],"media":[21],"platforms,":[22],"for":[23,56,142,200,232],"instance,":[24],"massive":[25,93],"user-generated":[26],"are":[28,158],"organized":[29],"across":[30,105,174],"related":[31],"tables":[32],"such":[33],"as":[34,70],"users,":[35],"posts,":[36],"comments,":[37],"and":[38,43,86,97,114,154,168,225],"interactions,":[39],"enabling":[40],"large-scale":[41,128],"analysis":[42],"predictive":[44,57,137],"modeling":[45],"behaviors.":[48],"To":[49,108,171],"effectively":[50],"use":[51],"knowledge":[53],"within":[54],"RDBs":[55,129,209],"tasks,":[58,227],"recent":[59],"advances":[60],"leverage":[61],"graph":[62],"representation":[63],"learning":[64,234],"to":[65,91,126],"capture":[66],"complex":[67],"inter-table":[68],"relations":[69,157],"multi-hop":[71],"dependencies.":[72],"Despite":[73],"achieving":[74],"state-of-the-art":[75],"performance,":[76],"these":[77,110],"methods":[78],"remain":[79],"hindered":[80],"by":[81],"prohibitive":[83],"storage":[84],"overhead":[85],"excessive":[87],"training":[88,143],"time,":[89],"due":[90],"scale":[94],"database":[96],"computational":[99],"burden":[100],"intensive":[102],"message":[103],"passing":[104],"interconnected":[106],"alleviate":[109],"concerns,":[111],"we":[112,124,186],"propose":[113],"study":[115],"problem":[117],"Database":[120],"Distillation":[121],"(RDD).":[122],"Specifically,":[123],"aim":[125],"distill":[127],"compact":[131],"heterogeneous":[132,161],"graphs":[133],"while":[134,219],"retaining":[135],"power":[138],"(i.e.,":[139],"utility)":[140],"required":[141],"graph-based":[144],"models.":[145],"Multi-modal":[146],"column":[147],"preserved":[150],"through":[151],"node":[152],"features,":[153],"primary\u2013foreign":[155],"key":[156],"encoded":[159],"via":[160],"edges,":[162],"thereby":[163],"maintaining":[164,220],"both":[165],"fidelity":[167],"relational":[169],"structure.":[170],"ensure":[172],"adaptability":[173],"diverse":[175],"downstream":[176],"tasks":[177],"without":[178],"engaging":[179],"traditional,":[181],"inefficient":[182],"bi-level":[183],"distillation":[184],"framework,":[185],"further":[187],"design":[188],"a":[189],"kernel":[190],"ridge":[191],"regression-guided":[192],"objective":[193],"with":[194,235],"pseudo-labels,":[195],"which":[196],"produces":[197],"quality":[198],"features":[199],"distilled":[202],"graph.":[203],"Extensive":[204],"experiments":[205],"on":[206,223],"real-world":[208],"demonstrate":[210],"that":[211],"our":[212],"solution":[213],"substantially":[214],"reduces":[215],"size":[218],"competitive":[221],"performances":[222],"classification":[224],"regression":[226],"creating":[228],"an":[229],"effective":[230],"pathway":[231],"scalable":[233],"RDBs.":[236]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-18T00:00:00"}