{"id":"https://openalex.org/W7131848748","doi":"https://doi.org/10.48550/arxiv.2602.22552","title":"Relatron: Automating Relational Machine Learning over Relational Databases","display_name":"Relatron: Automating Relational Machine Learning over Relational Databases","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131848748","doi":"https://doi.org/10.48550/arxiv.2602.22552"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.22552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22552","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.22552","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073466350","display_name":"Zhikai Chen","orcid":"https://orcid.org/0009-0009-7305-8629"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Zhikai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127276888","display_name":"Han Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127173093","display_name":"Jian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127278483","display_name":"Jiliang Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jiliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127130630","display_name":"Xiang Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127312342","display_name":"Huzefa Rangwala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rangwala, Huzefa","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5073466350"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11719","display_name":"Data Quality and Management","score":0.40230000019073486,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.40230000019073486,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.06069999933242798,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.040699999779462814,"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":0.6477000117301941},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.6240000128746033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5507000088691711},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5174999833106995},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5091999769210815},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4918000102043152},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43700000643730164},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.4171000123023987},{"id":"https://openalex.org/keywords/conjunctive-query","display_name":"Conjunctive query","score":0.3847000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458000183105469},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.6240000128746033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5999000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5975000262260437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.4171000123023987},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C65647387","wikidata":"https://www.wikidata.org/wiki/Q1781706","display_name":"Conjunctive query","level":3,"score":0.3847000002861023},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C2779812341","wikidata":"https://www.wikidata.org/wiki/Q5891525","display_name":"Homophily","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C141141315","wikidata":"https://www.wikidata.org/wiki/Q2379942","display_name":"Guard (computer science)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2680000066757202}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.22552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22552","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:10.48550/arxiv.2602.22552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22552","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":false,"raw_source_name":null,"raw_type":"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":{"Predictive":[0],"modeling":[1],"over":[2,53,242],"relational":[3],"databases":[4],"(RDBs)":[5],"powers":[6],"applications,":[7],"yet":[8],"remains":[9],"challenging":[10],"due":[11],"to":[12,143,239],"capturing":[13],"both":[14],"cross-table":[15],"dependencies":[16],"and":[17,55,74,81,121,158,167,176,203,205],"complex":[18],"feature":[19,27],"interactions.":[20],"Relational":[21],"Deep":[22,36],"Learning":[23],"(RDL)":[24],"methods":[25],"automate":[26],"engineering":[28],"via":[29],"message":[30],"passing,":[31],"while":[32],"classical":[33],"approaches":[34],"like":[35],"Feature":[37],"Synthesis":[38],"(DFS)":[39],"rely":[40],"on":[41],"predefined":[42],"non-parametric":[43],"aggregators.":[44],"Despite":[45],"performance":[46,103,137,156],"gains,":[47],"the":[48,56,115,151,154,183,207,226],"comparative":[49],"advantages":[50],"of":[51,153],"RDL":[52,73,96,202],"DFS":[54,75,204],"design":[57,79],"principles":[58],"for":[59,117,129],"selecting":[60],"effective":[61],"architectures":[62],"remain":[63],"poorly":[64],"understood.":[65],"We":[66],"present":[67],"a":[68,77,135,195],"comprehensive":[69],"study":[70],"that":[71,139,171,199],"unifies":[72],"in":[76,233],"shared":[78],"space":[80],"conducts":[82],"architecture-centric":[83],"searches":[84],"across":[85,112],"diverse":[86],"RDB":[87,164],"tasks.":[88],"Our":[89],"analysis":[90],"yields":[91,134],"three":[92],"key":[93],"findings:":[94],"(1)":[95],"does":[97],"not":[98],"consistently":[99],"outperform":[100],"DFS,":[101],"with":[102,182,245],"being":[104],"highly":[105],"task-dependent;":[106],"(2)":[107],"no":[108],"single":[109],"architecture":[110,130,141],"dominates":[111],"tasks,":[113],"underscoring":[114],"need":[116],"task-aware":[118],"model":[119,136],"selection;":[120],"(3)":[122],"validation":[123],"accuracy":[124],"is":[125],"an":[126,168],"unreliable":[127],"guide":[128],"choice.":[131],"This":[132],"search":[133],"bank":[138],"links":[140],"configurations":[142],"their":[144],"performance;":[145],"leveraging":[146],"this":[147],"bank,":[148],"we":[149,192],"analyze":[150],"drivers":[152],"RDL-DFS":[155],"gap":[157,184],"introduce":[159],"two":[160],"task":[161,165,196],"signals":[162],"--":[163,179],"homophily":[166],"affinity":[169],"embedding":[170],"captures":[172],"size,":[173],"path,":[174],"feature,":[175],"temporal":[177],"structure":[178],"whose":[180],"correlation":[181],"enables":[185],"principled":[186],"routing.":[187],"Guided":[188],"by":[189,218],"these":[190],"signals,":[191],"propose":[193],"Relatron,":[194],"embedding-based":[197],"meta-selector":[198],"chooses":[200],"between":[201],"prunes":[206],"within-family":[208],"search.":[209],"Lightweight":[210],"loss-landscape":[211],"metrics":[212],"further":[213],"guard":[214],"against":[215],"brittle":[216],"checkpoints":[217],"preferring":[219],"flatter":[220],"optima.":[221],"In":[222],"experiments,":[223],"Relatron":[224],"resolves":[225],"\"more":[227],"tuning,":[228],"worse":[229],"performance\"":[230],"effect":[231],"and,":[232],"joint":[234],"hyperparameter-architecture":[235],"optimization,":[236],"achieves":[237],"up":[238],"18.5%":[240],"improvement":[241],"strong":[243],"baselines":[244],"10x":[246],"lower":[247],"cost":[248],"than":[249],"Fisher":[250],"information-based":[251],"alternatives.":[252]},"counts_by_year":[],"updated_date":"2026-02-28T06:18:59.386488","created_date":"2026-02-28T00:00:00"}