{"id":"https://openalex.org/W2954727071","doi":"https://doi.org/10.14778/3329772.3329774","title":"Balance-aware distributed string similarity-based query processing system","display_name":"Balance-aware distributed string similarity-based query processing system","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2954727071","doi":"https://doi.org/10.14778/3329772.3329774","mag":"2954727071"},"language":"en","primary_location":{"id":"doi:10.14778/3329772.3329774","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3329772.3329774","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":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101588053","display_name":"Ji Sun","orcid":"https://orcid.org/0000-0002-9782-7201"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Sun","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007330751","display_name":"Zeyuan Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyuan Shang","raw_affiliation_strings":["Tsinghua University and MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University and MIT","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Deng","raw_affiliation_strings":["Tsinghua University and MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University and MIT","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080660416","display_name":"Zhifeng Bao","orcid":"https://orcid.org/0000-0003-2477-381X"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Zhifeng Bao","raw_affiliation_strings":["RMIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.264,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88554779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":"9","first_page":"961","last_page":"974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T11106","display_name":"Data Management and Algorithms","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8296788334846497},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6760750412940979},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6620485782623291},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5813935995101929},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5801297426223755},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5150396823883057},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.45198097825050354},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.43051066994667053},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4126219153404236},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3120272159576416},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.29645252227783203},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.26795631647109985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16935878992080688},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.162181556224823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296788334846497},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6760750412940979},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6620485782623291},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5813935995101929},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5801297426223755},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5150396823883057},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.45198097825050354},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.43051066994667053},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4126219153404236},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3120272159576416},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29645252227783203},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.26795631647109985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16935878992080688},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.162181556224823},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3329772.3329774","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3329772.3329774","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"},{"id":"pmh:oai:figshare.com:article/27404316","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27404316","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1536525420","https://openalex.org/W1973001156","https://openalex.org/W1979666709","https://openalex.org/W1990947147","https://openalex.org/W1991175610","https://openalex.org/W1991800036","https://openalex.org/W2001700730","https://openalex.org/W2073112656","https://openalex.org/W2073329022","https://openalex.org/W2083854694","https://openalex.org/W2093270024","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2104599107","https://openalex.org/W2105423800","https://openalex.org/W2105436061","https://openalex.org/W2119057313","https://openalex.org/W2121269638","https://openalex.org/W2125980212","https://openalex.org/W2127675794","https://openalex.org/W2131815873","https://openalex.org/W2147717514","https://openalex.org/W2148148676","https://openalex.org/W2150916025","https://openalex.org/W2151930506","https://openalex.org/W2154658848","https://openalex.org/W2156855109","https://openalex.org/W2161936973","https://openalex.org/W2166400748","https://openalex.org/W2167331726","https://openalex.org/W2167847032","https://openalex.org/W2169387919","https://openalex.org/W2170478076","https://openalex.org/W2173213060","https://openalex.org/W2286724461","https://openalex.org/W2294331997","https://openalex.org/W2513214219","https://openalex.org/W2542998387","https://openalex.org/W2562696781","https://openalex.org/W2612526608","https://openalex.org/W2742637748","https://openalex.org/W2752274179","https://openalex.org/W2792196230","https://openalex.org/W2798412430","https://openalex.org/W2891345706","https://openalex.org/W2929353582","https://openalex.org/W6674576723","https://openalex.org/W6683401941","https://openalex.org/W6749274700"],"related_works":["https://openalex.org/W2006459955","https://openalex.org/W2955368753","https://openalex.org/W3125756434","https://openalex.org/W2184296057","https://openalex.org/W2558523485","https://openalex.org/W203907944","https://openalex.org/W4386051213","https://openalex.org/W2096359267","https://openalex.org/W2992414350","https://openalex.org/W4379407450"],"abstract_inverted_index":{"Data":[0],"analysts":[1],"spend":[2],"more":[3],"than":[4],"80%":[5],"of":[6,17,152,178,219],"time":[7],"on":[8,196,204],"data":[9,18,22,99,105],"cleaning":[10],"and":[11,24,37,46,82,125,141,167,221],"integration":[12],"in":[13,97,107,173],"the":[14,35,130,134,153,176,183],"whole":[15],"process":[16],"analytics":[19],"due":[20],"to":[21,33,91,132,144],"errors":[23,36],"inconsistencies.":[25,38],"Similarity-based":[26],"query":[27,41,63,170,194],"processing":[28,42,64,195],"is":[29,43,150,182],"an":[30],"important":[31],"way":[32],"tolerate":[34],"However,":[39],"similarity-based":[40,62,95,193],"rather":[44],"costly":[45],"traditional":[47],"database":[48],"cannot":[49],"afford":[50],"such":[51],"expensive":[52,104],"requirement.":[53],"In":[54],"this":[55,181],"paper,":[56],"we":[57,111,126,160],"develop":[58],"a":[59,108],"distributed":[60,109,156,186],"in-memory":[61,157,187],"system":[65,188],"called":[66],"Dima.":[67],"Dima":[68,86,136,164,212],"supports":[69],"four":[70,205],"core":[71],"similarity":[72,75,77,146],"operations,":[73],"i.e.,":[74],"selection,":[76],"join,":[78],"top-":[79,83],"k":[80,84],"selection":[81],"join.":[85],"extends":[87],"SQL":[88],"for":[89],"users":[90],"easily":[92],"invoke":[93],"these":[94],"operations":[96],"their":[98],"analysis":[100],"tasks.":[101],"To":[102,175],"avoid":[103],"transmission":[106],"environment,":[110],"propose":[112],"balance-aware":[113],"signatures":[114,131],"where":[115],"two":[116],"records":[117],"are":[118],"similar":[119],"if":[120],"they":[121],"share":[122],"common":[123],"signatures,":[124],"can":[127,190],"adaptively":[128],"select":[129],"balance":[133],"workload.":[135],"builds":[137],"signature-based":[138],"global":[139],"indexes":[140,143],"local":[142],"support":[145,191],"operations.":[147],"Since":[148],"Spark":[149,166],"one":[151],"widely":[154],"adopted":[155],"computing":[158],"systems,":[159],"have":[161,200],"seamlessly":[162],"integrated":[163],"into":[165],"developed":[168],"effective":[169],"optimization":[171],"techniques":[172],"Spark.":[174],"best":[177],"our":[179],"knowledge,":[180],"first":[184],"full-fledged":[185],"that":[189,211],"complex":[192],"large-scale":[197],"datasets.":[198,207],"We":[199],"conducted":[201],"extensive":[202],"experiments":[203],"real-world":[206],"Experimental":[208],"results":[209],"show":[210],"outperforms":[213],"state-of-the-art":[214],"studies":[215],"by":[216],"1--3":[217],"orders":[218],"magnitude":[220],"has":[222],"good":[223],"scalability.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}