{"id":"https://openalex.org/W4411403241","doi":"https://doi.org/10.1145/3725365","title":"Table Overlap Estimation through Graph Embeddings","display_name":"Table Overlap Estimation through Graph Embeddings","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411403241","doi":"https://doi.org/10.1145/3725365"},"language":"en","primary_location":{"id":"doi:10.1145/3725365","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725365","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3725365","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118330976","display_name":"Francesco Pugnaloni","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Francesco Pugnaloni","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061991280","display_name":"Luca Zecchini","orcid":"https://orcid.org/0000-0002-4856-0838"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Zecchini","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037298798","display_name":"Matteo Paganelli","orcid":"https://orcid.org/0000-0001-8119-895X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Paganelli","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084898176","display_name":"Matteo Lissandrini","orcid":null},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Lissandrini","raw_affiliation_strings":["University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047630333","display_name":"Giovanni Simonini","orcid":"https://orcid.org/0000-0002-3466-509X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Simonini","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5118330976"],"corresponding_institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":2.1106,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87285216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9930999875068665,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/table","display_name":"Table (database)","score":0.8046184778213501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628216743469238},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5399717092514038},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5074040293693542},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4905549883842468},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46382537484169006},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45423030853271484},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4495224356651306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34019938111305237},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3289646506309509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31015586853027344}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8046184778213501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628216743469238},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5399717092514038},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5074040293693542},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4905549883842468},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46382537484169006},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45423030853271484},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4495224356651306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34019938111305237},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3289646506309509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31015586853027344},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3725365","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725365","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:iris.unimore.it:11380/1380989","is_oa":false,"landing_page_url":"https://hdl.handle.net/11380/1380989","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3725365","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725365","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1521736627","https://openalex.org/W1969621019","https://openalex.org/W2069870183","https://openalex.org/W2493916176","https://openalex.org/W2747329762","https://openalex.org/W2798664493","https://openalex.org/W2899286282","https://openalex.org/W2903025523","https://openalex.org/W2962756421","https://openalex.org/W2970066309","https://openalex.org/W2970992672","https://openalex.org/W2971681342","https://openalex.org/W2997169693","https://openalex.org/W3014616325","https://openalex.org/W3035231859","https://openalex.org/W3093679380","https://openalex.org/W3102264439","https://openalex.org/W3103177583","https://openalex.org/W3145728363","https://openalex.org/W3174380000","https://openalex.org/W4205196528","https://openalex.org/W4229641819","https://openalex.org/W4281826654","https://openalex.org/W4285335450","https://openalex.org/W4310390625","https://openalex.org/W4321448337","https://openalex.org/W4365456672","https://openalex.org/W4375928372","https://openalex.org/W4380433117","https://openalex.org/W4393180082","https://openalex.org/W6601955380","https://openalex.org/W6732946568","https://openalex.org/W6767098714"],"related_works":["https://openalex.org/W2389818373","https://openalex.org/W4392445444","https://openalex.org/W4396220545","https://openalex.org/W2220831889","https://openalex.org/W4312683641","https://openalex.org/W3027421045","https://openalex.org/W4405933298","https://openalex.org/W3013312691","https://openalex.org/W2980386803","https://openalex.org/W3215994059"],"abstract_inverted_index":{"Discovering":[0],"duplicate":[1,36],"or":[2,37],"high-overlapping":[3],"tables":[4,39,181],"in":[5,18,133,194],"table":[6,23,53,87,104,124,132,149,154],"collections":[7],"is":[8,173],"a":[9,22,147,191],"crucial":[10],"task":[11,43],"for":[12,58,65,73,84],"eliminating":[13],"redundant":[14],"information,":[15],"detecting":[16],"inconsistencies":[17],"the":[19,48,51,69,110,116,119,127,130,134,162,186,196],"evolution":[20],"of":[21,50,81,121,129,164,180],"across":[24],"its":[25,74],"multiple":[26],"versions":[27],"produced":[28],"over":[29],"time,":[30],"and":[31,126,146],"identifying":[32],"related":[33,38],"tables.":[34],"Candidate":[35],"to":[40,175],"support":[41],"this":[42,90],"can":[44],"be":[45],"identified":[46],"via":[47],"estimation":[49],"largest":[52,123],"overlap.":[54,160],"Unfortunately,":[55],"current":[56],"solutions":[57],"finding":[59],"it":[60,172],"present":[61],"serious":[62],"scalability":[63],"issues":[64],"heavy":[66],"workloads:":[67],"Sloth,":[68],"state":[70],"of-the-art":[71],"framework":[72],"estimation,":[75],"requires":[76],"more":[77],"than":[78,185],"three":[79],"days":[80],"machine":[82],"time":[83],"computing":[85],"100k":[86],"overlaps.":[88],"In":[89],"paper,":[91],"we":[92,169],"introduce":[93,138],"ARMADILLO,":[94],"an":[95],"approach":[96],"based":[97,143],"on":[98,144,166],"graph":[99],"neural":[100],"networks":[101],"that":[102,171],"learns":[103],"embeddings":[105],"whose":[106],"cosine":[107],"similarity":[108],"approximates":[109],"overlap":[111,125],"ratio":[112,117],"between":[113,118,178],"tables,":[114],"i.e.,":[115],"area":[120,128],"their":[122,159],"smaller":[131],"pair.":[135],"We":[136],"also":[137],"two":[139],"new":[140],"annotated":[141],"datasets":[142],"GitTables":[145],"Wikipedia":[148],"corpus":[150],"containing":[151],"1.32":[152],"million":[153],"pairs":[155,179],"overall":[156],"labeled":[157],"with":[158],"Evaluating":[161],"performance":[163],"ARMADILLO":[165],"these":[167],"datasets,":[168],"observed":[170],"able":[174],"calculate":[176],"overlaps":[177],"several":[182],"times":[183],"faster":[184],"state-of-the-art":[187],"method":[188],"while":[189],"maintaining":[190],"good":[192],"quality":[193],"approximating":[195],"exact":[197],"result.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}