{"id":"https://openalex.org/W3009602721","doi":"https://doi.org/10.1109/tkde.2021.3091101","title":"Data Lake Organization","display_name":"Data Lake Organization","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3009602721","doi":"https://doi.org/10.1109/tkde.2021.3091101","mag":"3009602721"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3091101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3091101","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.07024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012572863","display_name":"Fatemeh Nargesian","orcid":"https://orcid.org/0000-0002-4710-8719"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fatemeh Nargesian","raw_affiliation_strings":["Computer Science, University of Rochester, Rochester, New York, United States, (e-mail: f.nargesian@rochester.edu)","University of Rochester"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Rochester, Rochester, New York, United States, (e-mail: f.nargesian@rochester.edu)","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108778575","display_name":"Ken Q. Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"University of Ontario Institute of Technology","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ken Qian Pu","raw_affiliation_strings":["Faculty of Science, University of Ontario Institute of Technology, Oshawa, Ontario, Canada, (e-mail: ken.pu@uoit.ca)","University of Ontario Institute of Tech"],"affiliations":[{"raw_affiliation_string":"Faculty of Science, University of Ontario Institute of Technology, Oshawa, Ontario, Canada, (e-mail: ken.pu@uoit.ca)","institution_ids":["https://openalex.org/I39470171"]},{"raw_affiliation_string":"University of Ontario Institute of Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044982088","display_name":"Bahar Ghadiri Bashardoost","orcid":"https://orcid.org/0000-0001-8654-6626"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I4210117449","display_name":"Canadian Sugar Institute","ror":"https://ror.org/02jnh1883","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210117449"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Bahar Ghadiri Bashardoost","raw_affiliation_strings":["Computer Science, University of Toronto, 7938 Toronto, Ontario, Canada, (e-mail: ghadiri@cs.toronto.edu)","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Toronto, 7938 Toronto, Ontario, Canada, (e-mail: ghadiri@cs.toronto.edu)","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210117449"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013934423","display_name":"Erkang Zhu","orcid":"https://orcid.org/0009-0000-3326-1790"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Erkang Zhu","raw_affiliation_strings":["Data Management, Exploration and Mining (DMX), Microsoft Corp, 6834 Redmond, Washington, United States, (e-mail: ekzhu@microsoft.com)","University of Toronto"],"affiliations":[{"raw_affiliation_string":"Data Management, Exploration and Mining (DMX), Microsoft Corp, 6834 Redmond, Washington, United States, (e-mail: ekzhu@microsoft.com)","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Renee J. Miller","raw_affiliation_strings":["Computer Science, Northeastern University, 1848 Boston, Massachusetts, United States, (e-mail: miller@northeastern.edu)","Northeastern University"],"affiliations":[{"raw_affiliation_string":"Computer Science, Northeastern University, 1848 Boston, Massachusetts, United States, (e-mail: miller@northeastern.edu)","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012572863"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":0.20048996,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47380936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9962999820709229,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.7491074800491333},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5726621150970459},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.570501446723938},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5166671276092529},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5156470537185669},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5155677795410156},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4338851869106293},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3894878029823303},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21257230639457703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14443069696426392}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491074800491333},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5726621150970459},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.570501446723938},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5166671276092529},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5156470537185669},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5155677795410156},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4338851869106293},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3894878029823303},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21257230639457703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14443069696426392},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tkde.2021.3091101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3091101","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1812.07024","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07024","pdf_url":"https://arxiv.org/pdf/1812.07024","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":"mag:3009602721","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1812.07024.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1812.07024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1812.07024","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:1812.07024","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07024","pdf_url":"https://arxiv.org/pdf/1812.07024","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":[{"id":"https://metadata.un.org/sdg/14","score":0.5299999713897705,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W38703128","https://openalex.org/W87092222","https://openalex.org/W110972138","https://openalex.org/W574700118","https://openalex.org/W1494397996","https://openalex.org/W1532325895","https://openalex.org/W1604957788","https://openalex.org/W1815331012","https://openalex.org/W1969621019","https://openalex.org/W1981706510","https://openalex.org/W1983305952","https://openalex.org/W2022166150","https://openalex.org/W2029344051","https://openalex.org/W2066806792","https://openalex.org/W2092364718","https://openalex.org/W2105481243","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2116066543","https://openalex.org/W2139902660","https://openalex.org/W2140116426","https://openalex.org/W2144108169","https://openalex.org/W2144452830","https://openalex.org/W2144731007","https://openalex.org/W2153579005","https://openalex.org/W2155734303","https://openalex.org/W2160605923","https://openalex.org/W2216189112","https://openalex.org/W2233447580","https://openalex.org/W2239306219","https://openalex.org/W2250539671","https://openalex.org/W2252211299","https://openalex.org/W2295598076","https://openalex.org/W2340354588","https://openalex.org/W2403920869","https://openalex.org/W2438792749","https://openalex.org/W2533904613","https://openalex.org/W2584580687","https://openalex.org/W2585438896","https://openalex.org/W2624356872","https://openalex.org/W2750991217","https://openalex.org/W2795089200","https://openalex.org/W2795302121","https://openalex.org/W2798664493","https://openalex.org/W2800982342","https://openalex.org/W2810954846","https://openalex.org/W2898269683","https://openalex.org/W2923400109","https://openalex.org/W2926805670","https://openalex.org/W2948163032","https://openalex.org/W2951621897","https://openalex.org/W2963174348","https://openalex.org/W2963626623","https://openalex.org/W3014616325","https://openalex.org/W3031051334","https://openalex.org/W3032215537","https://openalex.org/W3102476541","https://openalex.org/W4213009331","https://openalex.org/W6601548560","https://openalex.org/W6629688113","https://openalex.org/W6636120121","https://openalex.org/W6645513334","https://openalex.org/W6682691769","https://openalex.org/W6683861112","https://openalex.org/W6691227101","https://openalex.org/W6713622676","https://openalex.org/W6732710093","https://openalex.org/W6733170484","https://openalex.org/W6749511090","https://openalex.org/W6750444872","https://openalex.org/W6753529518"],"related_works":["https://openalex.org/W2904132383","https://openalex.org/W1974124545","https://openalex.org/W2000623017","https://openalex.org/W2951183147","https://openalex.org/W2767652101","https://openalex.org/W2330506098","https://openalex.org/W2114079787","https://openalex.org/W3165875863","https://openalex.org/W2944413666","https://openalex.org/W2122516730","https://openalex.org/W2742144031","https://openalex.org/W2783919036","https://openalex.org/W2188345419","https://openalex.org/W25677450","https://openalex.org/W2402159371","https://openalex.org/W2604533041","https://openalex.org/W2957640754","https://openalex.org/W2951183003","https://openalex.org/W2097427044","https://openalex.org/W3212755951"],"abstract_inverted_index":{"We":[0,20,45,71,97,108],"consider":[1],"the":[2,60,69,73,79,87,103,110,113,131,169,202],"problem":[3,77,80],"of":[4,32,51,62,81,90,112,134,166,171],"creating":[5],"a":[6,11,17,25,35,47,63,66,139,213],"navigation":[7,146,172],"structure":[8],"that":[9,27,85,129,145,153,195],"allows":[10],"user":[12,64,141],"to":[13],"most":[14],"effectively":[15],"navigate":[16],"data":[18,36,74,104,118,121,124,136,187,190,196,203],"lake.":[19],"define":[21,59],"an":[22,56,83,95,99,208],"organization":[23,57,76,84,106],"as":[24,78],"graph":[26],"contains":[28],"nodes":[29],"representing":[30],"sets":[31],"attributes":[33],"within":[34],"lake":[37,75,105,197,204],"and":[38,58,126,173,182,206,212],"edges":[39],"indicating":[40],"subset":[41],"relationships":[42],"among":[43],"nodes.":[44],"present":[46],"new":[48],"probabilistic":[49],"model":[50],"how":[52],"users":[53,149,167],"interact":[54],"with":[55],"likelihood":[61],"finding":[65,82],"table":[67],"using":[68],"organization.":[70,96,216],"propose":[72,98],"maximizes":[86],"expected":[88],"probability":[89],"discovering":[91],"tables":[92,152],"by":[93,157],"navigating":[94],"approximate":[100],"algorithm":[101,114],"for":[102,186],"problem.":[107],"show":[109,144,194],"effectiveness":[111],"on":[115,127],"both":[116,183],"real":[117,135],"lakes":[119],"containing":[120],"from":[122],"open":[123],"portals":[125],"benchmarks":[128],"emulate":[130],"observed":[132],"characteristics":[133],"lakes.":[137,191],"Through":[138],"formal":[140],"study,":[142,164],"we":[143],"can":[147],"help":[148],"discover":[150],"relevant":[151],"cannot":[154],"be":[155],"found":[156],"keyword":[158,176],"search.":[159],"In":[160],"addition,":[161],"in":[162,189],"our":[163],"42%":[165],"preferred":[168,175],"use":[170],"58%":[174],"search,":[177],"suggesting":[178],"these":[179],"are":[180],"complementary":[181],"useful":[184],"modalities":[185],"discovery":[188],"Our":[192],"experiments":[193],"organizations":[198],"take":[199],"into":[200],"account":[201],"distribution":[205],"outperform":[207],"existing":[209],"hand-curated":[210],"taxonomy":[211],"common":[214],"baseline":[215]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}