{"id":"https://openalex.org/W2954675436","doi":"https://doi.org/10.1109/tbdata.2019.2907116","title":"Efficient Provenance Management via Clustering and Hybrid Storage in Big Data Environments","display_name":"Efficient Provenance Management via Clustering and Hybrid Storage in Big Data Environments","publication_year":2019,"publication_date":"2019-03-25","ids":{"openalex":"https://openalex.org/W2954675436","doi":"https://doi.org/10.1109/tbdata.2019.2907116","mag":"2954675436"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2019.2907116","doi":"https://doi.org/10.1109/tbdata.2019.2907116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907116","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core","dongbi-b","jufo-1","norway-1","poland-70","russia-white-list-1"],"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 Big Data","raw_type":"journal-article"},"volume":null,"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/A5101490176","display_name":"Die Hu","orcid":"https://orcid.org/0000-0001-6134-1616","observed_orcids":["https://orcid.org/0000-0001-6134-1616"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Die Hu","raw_affiliation_strings":["School of Computer, Key Laboratory of Information Storage System, Ministry of Education of China, Huazhong University of Science and Technology, Wuhan, P.R. China"],"raw_orcid":"https://orcid.org/0000-0001-6134-1616","affiliations":[{"raw_affiliation_string":"School of Computer, Key Laboratory of Information Storage System, Ministry of Education of China, Huazhong University of Science and Technology, Wuhan, P.R. China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057421680","display_name":"Dan Feng","orcid":"https://orcid.org/0000-0002-4674-6006","observed_orcids":["https://orcid.org/0000-0002-4674-6006"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Feng","raw_affiliation_strings":["School of Computer, Key Laboratory of Information Storage System, Ministry of Education of China, Huazhong University of Science and Technology, Wuhan, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Key Laboratory of Information Storage System, Ministry of Education of China, Huazhong University of Science and Technology, Wuhan, P.R. China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054468864","display_name":"Yulai Xie","orcid":"https://orcid.org/0000-0001-5757-4396","observed_orcids":["https://orcid.org/0000-0001-5757-4396"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulai Xie","raw_affiliation_strings":["School of Computer, Huazhong University of Science and Technology, Wuhan, P.R. China"],"raw_orcid":"https://orcid.org/0000-0001-5757-4396","affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, P.R. China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054889577","display_name":"Gongming Xu","orcid":"https://orcid.org/0000-0001-8024-1565","observed_orcids":["https://orcid.org/0000-0001-8024-1565"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongming Xu","raw_affiliation_strings":["School of Computer, Huazhong University of Science and Technology, Wuhan, P.R. China"],"raw_orcid":"https://orcid.org/0000-0001-8024-1565","affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, P.R. China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013000671","display_name":"Xinrui Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrui Gu","raw_affiliation_strings":["School of Computer, Key Laboratory of Information Storage System, Ministry of Education of China, Huazhong University of Science and Technology, Wuhan, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Key Laboratory of Information Storage System, Ministry of Education of China, Huazhong University of Science and Technology, Wuhan, P.R. China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029994088","display_name":"Darrell D. E. Long","orcid":"https://orcid.org/0000-0002-0822-0740","observed_orcids":["https://orcid.org/0000-0002-0822-0740"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darrell Long","raw_affiliation_strings":["Jack Baskin School of Engineering, University of California, Santa Cruz, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0822-0740","affiliations":[{"raw_affiliation_string":"Jack Baskin School of Engineering, University of California, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":3.8512,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94545533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":"4","first_page":"792","last_page":"803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.32249999046325684,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.32249999046325684,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.14509999752044678,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.13120000064373016,"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/provenance-management","display_name":"provenance management","score":0.9319999814033508},{"id":"https://openalex.org/keywords/label-propagation","display_name":"label propagation","score":0.777999997138977},{"id":"https://openalex.org/keywords/hybrid-storage-systems","display_name":"hybrid storage","score":0.9309999942779541},{"id":"https://openalex.org/keywords/data-compression","display_name":"data compression","score":0.5189999938011169},{"id":"https://openalex.org/keywords/feedback-mechanisms","display_name":"feedback mechanisms","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843978762626648},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.6697292327880859},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6207320690155029},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6129041910171509},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4934772253036499},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4473438262939453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43094560503959656},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4208487570285797},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4165571928024292},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11961045861244202},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2019.2907116","doi":"https://doi.org/10.1109/tbdata.2019.2907116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907116","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core","dongbi-b","jufo-1","norway-1","poland-70","russia-white-list-1"],"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 Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2184068523","display_name":null,"funder_award_id":"U1705261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2413230818","display_name":null,"funder_award_id":"61821003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5539248298","display_name":null,"funder_award_id":"61772222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8625880965","display_name":null,"funder_award_id":"61402189","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W17915278","https://openalex.org/W71388611","https://openalex.org/W97496400","https://openalex.org/W168132470","https://openalex.org/W213142593","https://openalex.org/W1559528097","https://openalex.org/W1575826986","https://openalex.org/W1858703999","https://openalex.org/W2007474131","https://openalex.org/W2020877492","https://openalex.org/W2047899835","https://openalex.org/W2081276694","https://openalex.org/W2084333665","https://openalex.org/W2085031088","https://openalex.org/W2095436528","https://openalex.org/W2096347345","https://openalex.org/W2112525062","https://openalex.org/W2114228709","https://openalex.org/W2126091978","https://openalex.org/W2132202037","https://openalex.org/W2137842875","https://openalex.org/W2150062570","https://openalex.org/W2165068957","https://openalex.org/W2199638414","https://openalex.org/W2356757109","https://openalex.org/W2397699236","https://openalex.org/W2400243382","https://openalex.org/W2404483544","https://openalex.org/W2532844970","https://openalex.org/W2579106964","https://openalex.org/W2586435401","https://openalex.org/W2625355143","https://openalex.org/W2747669027","https://openalex.org/W2889379876","https://openalex.org/W2912520317","https://openalex.org/W7052303740"],"related_works":["https://openalex.org/W4400685744","https://openalex.org/W2081276694","https://openalex.org/W1765271930","https://openalex.org/W3037815620","https://openalex.org/W2137842875","https://openalex.org/W2369920593","https://openalex.org/W2112525062","https://openalex.org/W7095888740","https://openalex.org/W2605047947","https://openalex.org/W6889304034"],"abstract_inverted_index":{"Provenance":[0],"is":[1,77],"a":[2,20,36,71,83,110,126,158],"type":[3],"of":[4,12,23,39,53,86],"metadata":[5],"that":[6,148],"records":[7],"the":[8,48,134,141,149],"creation":[9],"and":[10,29,51,65,81,99,104,108,117,132],"transformation":[11],"data":[13,40,106,119,138],"objects.":[14],"It":[15],"has":[16,35],"been":[17],"applied":[18],"to":[19,79,101,140],"wide":[21],"variety":[22],"areas":[24],"such":[25,96],"as":[26,97],"security,":[27],"search,":[28],"experimental":[30,145],"documentation.":[31],"However,":[32],"provenance":[33,60,154],"usually":[34],"vast":[37],"amount":[38],"with":[41,157],"its":[42],"rapid":[43],"growth":[44],"rate":[45],"which":[46,76,114,129],"hinders":[47],"effective":[49],"extraction":[50],"application":[52],"provenance.":[54,88],"This":[55],"paper":[56],"proposes":[57],"an":[58],"efficient":[59],"management":[61],"system":[62,150],"via":[63],"clustering":[64],"hybrid":[66],"storage.":[67],"Specifically,":[68],"we":[69,90,124],"propose":[70],"Provenance-Based":[72],"Label":[73],"Propagation":[74],"Algorithm":[75],"able":[78],"regularize":[80],"cluster":[82],"large":[84],"number":[85],"irregular":[87],"Then,":[89],"use":[91],"separate":[92],"physical":[93],"storage":[94],"mediums,":[95],"SSD":[98],"HDD,":[100],"store":[102],"hot":[103],"cold":[105,137],"separately,":[107],"implement":[109,125],"hot/cold":[111],"scheduling":[112],"scheme":[113],"can":[115,130,151],"update":[116],"schedule":[118],"between":[120],"them":[121],"automatically.":[122],"Besides,":[123],"feedback":[127],"mechanism":[128],"locate":[131],"compress":[133],"rarely":[135],"used":[136],"according":[139],"query":[142,155],"request.":[143],"The":[144],"test":[146],"shows":[147],"significantly":[152],"improve":[153],"performance":[156],"small":[159],"run-time":[160],"overhead.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-07-12T00:00:00"}
