{"id":"https://openalex.org/W4381329706","doi":"https://doi.org/10.1145/3589780","title":"Vineyard: Optimizing Data Sharing in Data-Intensive Analytics","display_name":"Vineyard: Optimizing Data Sharing in Data-Intensive Analytics","publication_year":2023,"publication_date":"2023-06-13","ids":{"openalex":"https://openalex.org/W4381329706","doi":"https://doi.org/10.1145/3589780"},"language":"en","primary_location":{"id":"doi:10.1145/3589780","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589780","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018856303","display_name":"Wenyuan Yu","orcid":"https://orcid.org/0009-0006-5641-2452"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyuan Yu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5641-2452","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880370","display_name":"Tao He","orcid":"https://orcid.org/0009-0007-7687-7342"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao He","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7687-7342","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101855658","display_name":"Lei Wang","orcid":"https://orcid.org/0009-0001-7535-452X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7535-452X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650527","display_name":"Ke Meng","orcid":"https://orcid.org/0000-0002-3629-7892"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Meng","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3629-7892","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612687","display_name":"Ye Cao","orcid":"https://orcid.org/0009-0009-7273-0575"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Cao","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7273-0575","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055909011","display_name":"Diwen Zhu","orcid":"https://orcid.org/0009-0002-7175-0784"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diwen Zhu","raw_affiliation_strings":["Alibaba Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-7175-0784","affiliations":[{"raw_affiliation_string":"Alibaba Group, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036221075","display_name":"Sanhong Li","orcid":"https://orcid.org/0009-0000-2869-7944"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanhong Li","raw_affiliation_strings":["Alibaba Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-2869-7944","affiliations":[{"raw_affiliation_string":"Alibaba Group, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101943530","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0001-6851-1366"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6851-1366","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":2.0551,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8923936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"1","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8634227514266968},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.762337863445282},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.7016457915306091},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6366428136825562},{"id":"https://openalex.org/keywords/undo","display_name":"Undo","score":0.6230263710021973},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.576863706111908},{"id":"https://openalex.org/keywords/vineyard","display_name":"Vineyard","score":0.5634148120880127},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5343007445335388},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4436441957950592},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.41787615418434143},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24323812127113342},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19587934017181396},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.11941313743591309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8634227514266968},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.762337863445282},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.7016457915306091},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6366428136825562},{"id":"https://openalex.org/C2780154230","wikidata":"https://www.wikidata.org/wiki/Q513420","display_name":"Undo","level":2,"score":0.6230263710021973},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.576863706111908},{"id":"https://openalex.org/C2780924976","wikidata":"https://www.wikidata.org/wiki/Q22715","display_name":"Vineyard","level":2,"score":0.5634148120880127},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5343007445335388},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4436441957950592},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.41787615418434143},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24323812127113342},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19587934017181396},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.11941313743591309},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589780","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589780","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1642179982","https://openalex.org/W1993892970","https://openalex.org/W2038157364","https://openalex.org/W2094269821","https://openalex.org/W2116129553","https://openalex.org/W2119738171","https://openalex.org/W2124011064","https://openalex.org/W2542459869","https://openalex.org/W2577439380","https://openalex.org/W2912351665","https://openalex.org/W2949762319","https://openalex.org/W2970929262","https://openalex.org/W2979615946","https://openalex.org/W2981859891","https://openalex.org/W3001851942","https://openalex.org/W3013115102","https://openalex.org/W3196829622","https://openalex.org/W4238584892"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W3092201768","https://openalex.org/W2796632413","https://openalex.org/W2740083192","https://openalex.org/W2794907032","https://openalex.org/W4255802207","https://openalex.org/W4299701476","https://openalex.org/W2904574413","https://openalex.org/W2462007151"],"abstract_inverted_index":{"Modern":[0],"data":[1,20,35,81,94,125,152,202,219],"analytics":[2,203,220],"and":[3,9,49,54,67,103,135,191,201],"AI":[4],"jobs":[5,204],"become":[6],"increasingly":[7],"complex":[8,85],"involve":[10],"multiple":[11],"tasks":[12],"performed":[13],"on":[14,93,198],"specialized":[15],"systems.":[16],"Sharing":[17],"of":[18,159,210,218],"intermediate":[19,34,151],"between":[21],"different":[22,89],"systems":[23,83,90,169],"is":[24,36,39,107,179],"often":[25,108],"a":[26,64,129,171,175],"significant":[27],"bottleneck":[28],"in":[29,44,84,170,194],"such":[30,112,156],"jobs.":[31],"When":[32],"the":[33,160,207,215],"large,":[37],"it":[38,120],"mostly":[40],"exchanged":[41],"through":[42],"files":[43],"standard":[45],"formats":[46],"(e.g.,":[47,96],"CSV":[48],"ORC),":[50],"causing":[51],"high":[52,130,192],"I/O":[53],"(de)serialization":[55],"overheads.":[56],"To":[57],"solve":[58],"these":[59],"problems,":[60],"we":[61],"develop":[62],"Vineyard,":[63],"high-performance,":[65],"extensible,":[66],"cloud-native":[68,176],"object":[69],"store,":[70],"trying":[71],"to":[72,79,123,144,147,181,228],"provide":[73],"an":[74,140],"intuitive":[75],"experience":[76],"for":[77],"users":[78,146],"share":[80],"across":[82,168],"real-life":[86,199],"workflows.":[87],"Since":[88],"usually":[91],"work":[92,182],"structures":[95],"dataframes,":[97],"graphs,":[98],"hashmaps)":[99],"with":[100,110,184],"similar":[101],"interfaces,":[102],"their":[104,149,224],"computation":[105],"logic":[106],"loosely-coupled":[109],"how":[111],"interfaces":[113],"are":[114],"implemented":[115],"over":[116],"specific":[117],"memory":[118,133],"layouts,":[119],"enables":[121],"Vineyard":[122,138,155,178,211],"conduct":[124],"sharing":[126],"efficiently":[127,166],"at":[128],"level":[131],"via":[132],"mapping":[134],"method":[136],"sharing.":[137],"provides":[139],"IDL":[141],"named":[142],"VCDL":[143],"facilitate":[145],"register":[148],"own":[150],"types":[153,162],"into":[154],"that":[157,206],"objects":[158],"registered":[161],"can":[163,212],"then":[164],"be":[165],"shared":[167],"polyglot":[172],"workflow.":[173],"As":[174],"system,":[177],"designed":[180],"closely":[183],"Kubernetes,":[185],"as":[186,188],"well":[187],"achieve":[189],"fault-tolerance":[190],"performance":[193,217],"production":[195],"environments.":[196],"Evaluations":[197],"datasets":[200],"show":[205],"above":[208],"optimizations":[209],"significantly":[213],"improve":[214],"end-to-end":[216],"jobs,":[221],"by":[222],"reducing":[223],"data-sharing":[225],"time":[226],"up":[227],"68.4x.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
