{"id":"https://openalex.org/W2988852311","doi":"https://doi.org/10.1007/s41019-019-00107-y","title":"FreshJoin: An Efficient and Adaptive Algorithm for Set Containment Join","display_name":"FreshJoin: An Efficient and Adaptive Algorithm for Set Containment Join","publication_year":2019,"publication_date":"2019-11-09","ids":{"openalex":"https://openalex.org/W2988852311","doi":"https://doi.org/10.1007/s41019-019-00107-y","mag":"2988852311"},"language":"en","primary_location":{"id":"doi:10.1007/s41019-019-00107-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-00107-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00107-y.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00107-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089695189","display_name":"Jizhou Luo","orcid":"https://orcid.org/0000-0002-3302-3917"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jizhou Luo","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3302-3917","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018771","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0003-1818-4082"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069539054","display_name":"Shengfei Shi","orcid":"https://orcid.org/0000-0003-2932-4618"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengfei Shi","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070851627","display_name":"Hong Gao","orcid":"https://orcid.org/0000-0002-2000-6683"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Gao","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387065","display_name":"Jianzhong Li","orcid":"https://orcid.org/0000-0002-4119-0571"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101441233","display_name":"Wei Wu","orcid":"https://orcid.org/0009-0001-7309-201X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058283847","display_name":"Shouxu Jiang","orcid":"https://orcid.org/0000-0001-5692-0074"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouxu Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089695189"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":1290,"currency":"USD","value_usd":1290},"apc_paid":{"value":1290,"currency":"USD","value_usd":1290},"fwci":1.0692,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79667926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"4","issue":"4","first_page":"293","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9902999997138977,"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/T11106","display_name":"Data Management and Algorithms","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/algorithm","display_name":"Algorithm","score":0.7199850082397461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.668998122215271},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5818932056427002},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5769163370132446},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5583571195602417},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.46473005414009094},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45288634300231934},{"id":"https://openalex.org/keywords/hash-join","display_name":"Hash join","score":0.43564265966415405},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32713258266448975},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25796183943748474},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.20034950971603394},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08740660548210144}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.7199850082397461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.668998122215271},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5818932056427002},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5769163370132446},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5583571195602417},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.46473005414009094},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45288634300231934},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.43564265966415405},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32713258266448975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25796183943748474},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.20034950971603394},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08740660548210144},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s41019-019-00107-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-00107-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00107-y.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6114a1d0adfe4183b1adea3e39f7b6ea","is_oa":true,"landing_page_url":"https://doaj.org/article/6114a1d0adfe4183b1adea3e39f7b6ea","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science and Engineering, Vol 4, Iss 4, Pp 293-308 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s41019-019-00107-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-00107-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00107-y.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2988852311.pdf","grobid_xml":"https://content.openalex.org/works/W2988852311.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1487929601","https://openalex.org/W1502634995","https://openalex.org/W1519865830","https://openalex.org/W2010454887","https://openalex.org/W2054311069","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2100833709","https://openalex.org/W2105436061","https://openalex.org/W2111967310","https://openalex.org/W2118514362","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2128056631","https://openalex.org/W2134106518","https://openalex.org/W2141469207","https://openalex.org/W2167847032","https://openalex.org/W2251699075","https://openalex.org/W2255183403","https://openalex.org/W2294331997","https://openalex.org/W2396588571","https://openalex.org/W2474417011","https://openalex.org/W2615445578","https://openalex.org/W2771507595","https://openalex.org/W2950930616","https://openalex.org/W2963174348","https://openalex.org/W2963443080","https://openalex.org/W4298019065"],"related_works":["https://openalex.org/W2381211091","https://openalex.org/W2091359263","https://openalex.org/W2469706965","https://openalex.org/W1589496614","https://openalex.org/W2159860101","https://openalex.org/W1874105428","https://openalex.org/W4234452035","https://openalex.org/W3187487646","https://openalex.org/W1981952567","https://openalex.org/W1866159721"],"abstract_inverted_index":{"Abstract":[0],"This":[1,74],"paper":[2,75],"revisits":[3],"set":[4],"containment":[5],"join":[6,22,88],"(SCJ)":[7],"problem,":[8],"which":[9,149,192],"uses":[10],"the":[11,56,61,69,130,135,183,189,231],"subset":[12],"relationship":[13],"(i.e.,":[14,115],"$$\\subseteq$$":[15],"<mml:math":[16,92,102,168,200,216],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mo>\u2286</mml:mo></mml:math>":[17],")":[18],"as":[19,84,228,230],"condition":[20],"to":[21,96,109,196],"set-valued":[23],"attributes":[24],"of":[25,55,58,68,71,113,132,141,153,177,188,223],"two":[26,116,142,147],"relations":[27],"and":[28,35,120,146,185],"has":[29],"many":[30],"fundamental":[31],"applications":[32],"in":[33,94,134,156,234],"commercial":[34],"scientific":[36],"fields.":[37],"Existing":[38],"in-memory":[39,81],"algorithms":[40,233],"for":[41],"SCJ":[42,98],"are":[43,205],"either":[44],"signature-based":[45],"or":[46,89],"prefix-tree-based.":[47],"The":[48,138,159,175],"former":[49],"incurs":[50,63],"high":[51,64],"CPU":[52],"cost":[53,66,187,225],"because":[54,67],"enumeration":[57],"signatures,":[59],"while":[60,226],"latter":[62],"space":[65,186,224],"storage":[70],"prefix":[72],"trees.":[73],"proposes":[76],"a":[77,105,121,194],"new":[78],"adaptive":[79],"parameter-free":[80],"algorithm,":[82,191],"named":[83],"fre":[85],"quency-ha":[86],"sh":[87],"$${\\mathsf":[90,100,166,198,214],"{FreshJoin}}$$":[91,101,167,199,215],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mi>FreshJoin</mml:mi></mml:math>":[93,103,169,201,217],"short,":[95],"evaluate":[97],"efficiently.":[99],"builds":[104],"flat":[106],"index":[107,139,160],"on-the-fly":[108],"record":[110,150],"three":[111],"kinds":[112],"signatures":[114,152],"least":[117],"frequent":[118],"elements":[119,133],"hash":[122,151,173],"signature":[123],"whose":[124],"length":[125],"is":[126,161,180],"determined":[127],"adaptively":[128],"by":[129],"frequencies":[131],"universe":[136],"set).":[137],"consists":[140],"sparse":[143],"inverted":[144],"indices":[145],"arrays":[148],"all":[154],"sets":[155],"each":[157],"relation.":[158],"well":[162],"organized":[163],"such":[164],"that":[165,213],"can":[170],"avoid":[171],"enumerating":[172],"signatures.":[174],"rationality":[176],"this":[178],"design":[179],"explained.":[181],"And,":[182],"time":[184],"proposed":[190],"provide":[193],"rule":[195],"choose":[197],"from":[202],"existing":[203],"algorithms,":[204],"analyzed.":[206],"Experiments":[207],"on":[208],"16":[209],"real-life":[210],"datasets":[211],"show":[212],"usually":[218],"reduces":[219],"more":[220],"than":[221],"50%":[222],"remains":[227],"competitive":[229],"state-of-the-art":[232],"running":[235],"time.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
