{"id":"https://openalex.org/W4407679879","doi":"https://doi.org/10.14778/3704965.3704983","title":"Generalizable Data Cleaning of Tabular Data in Latent Space","display_name":"Generalizable Data Cleaning of Tabular Data in Latent Space","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4407679879","doi":"https://doi.org/10.14778/3704965.3704983"},"language":"en","primary_location":{"id":"doi:10.14778/3704965.3704983","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3704965.3704983","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000803349","display_name":"Eduardo M. Reis","orcid":"https://orcid.org/0000-0002-9556-3070"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Eduardo Reis","raw_affiliation_strings":["Technical University of Darmstadt"],"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031867487","display_name":"Mohamed Abdelaal","orcid":"https://orcid.org/0000-0001-8592-9510"},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]},{"id":"https://openalex.org/I4210087769","display_name":"Software AG (Italy)","ror":"https://ror.org/003jrsn97","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210087769"]}],"countries":["ES","IT"],"is_corresponding":false,"raw_author_name":"Mohamed Abdelaal","raw_affiliation_strings":["Software AG"],"affiliations":[{"raw_affiliation_string":"Software AG","institution_ids":["https://openalex.org/I97750245","https://openalex.org/I4210087769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073504200","display_name":"Carsten Binnig","orcid":"https://orcid.org/0000-0002-2744-7836"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Binnig","raw_affiliation_strings":["Technical University of Darmstadt & DFKI"],"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt & DFKI","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000803349"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25260979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"13","first_page":"4786","last_page":"4798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9987999796867371,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9987999796867371,"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":0.9987000226974487,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9869999885559082,"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/space","display_name":"Space (punctuation)","score":0.5786004662513733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4061077833175659},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.36903321743011475}],"concepts":[{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5786004662513733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4061077833175659},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.36903321743011475},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3704965.3704983","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3704965.3704983","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2298871042","https://openalex.org/W2548122763","https://openalex.org/W2591700809","https://openalex.org/W2607294481","https://openalex.org/W2769041395","https://openalex.org/W2929941791","https://openalex.org/W2959716049","https://openalex.org/W2987471611","https://openalex.org/W2997919412","https://openalex.org/W3105977086","https://openalex.org/W3110632587","https://openalex.org/W3147796863","https://openalex.org/W3161168558","https://openalex.org/W3175514463","https://openalex.org/W3197847098","https://openalex.org/W3198109053","https://openalex.org/W3198445485","https://openalex.org/W4205922070","https://openalex.org/W4243565423","https://openalex.org/W4286988404","https://openalex.org/W4301409532","https://openalex.org/W4317767732","https://openalex.org/W4372267129","https://openalex.org/W6772013027"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,12,164],"this":[1],"paper,":[2],"we":[3,32,40,100,123,154,167],"present":[4],"a":[5,77,93,181],"new":[6],"method":[7,18,110,147],"for":[8],"learned":[9],"data":[10,22,46,61,90],"cleaning.":[11],"contrast":[13],"to":[14,20,76],"existing":[15,173],"methods,":[16],"our":[17,121,134,165,170],"learns":[19],"clean":[21,45],"in":[23,71,97,150,188],"the":[24,35,42,82,85,108,131,151,161,184,189],"latent":[25,36,51,73,98],"space.":[26],"The":[27],"main":[28],"idea":[29],"is":[30],"that":[31,39,127,169,186],"(1)":[33],"shape":[34],"space":[37],"such":[38],"know":[41],"area":[43],"where":[44],"resides":[47],"and":[48,158],"(2)":[49],"learn":[50],"operators":[52],"trained":[53,178],"on":[54,142,179],"error":[55,135,145],"repair":[56,102,136,159],"(Lopster)":[57],"which":[58,111],"shift":[59,95],"erroneous":[60],"(e.g.,":[62],"table":[63],"rows":[64],"with":[65,120],"noise,":[66],"outliers,":[67],"or":[68],"missing":[69],"values)":[70],"their":[72],"representation":[74],"back":[75],"\"clean\"":[78],"region,":[79],"thus":[80],"abstracting":[81],"complexities":[83],"of":[84,105,133,183],"input":[86],"domain.":[87],"When":[88],"formulating":[89],"cleaning":[91,174],"as":[92,148],"simple":[94],"operation":[96],"space,":[99],"can":[101,124],"all":[103],"types":[104],"errors":[106,126,185],"using":[107],"same":[109],"makes":[112],"it":[113],"more":[114],"robust":[115],"than":[116],"other":[117],"methods.":[118],"Importantly,":[119],"method,":[122],"handle":[125,155],"are":[128],"unseen":[129],"during":[130],"training":[132],"model.":[137],"We":[138],"do":[139],"not":[140],"rely":[141],"an":[143],"external":[144],"detection":[146,157],"seen":[149],"state-of-the-art,":[152],"instead,":[153],"both":[156],"within":[160],"Lopster":[162],"framework.":[163],"evaluation,":[166],"show":[168],"approach":[171],"outperforms":[172],"methods":[175],"even":[176],"when":[177],"only":[180],"subset":[182],"occur":[187],"dirty":[190],"data.":[191]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}