{"id":"https://openalex.org/W2346147088","doi":"https://doi.org/10.1109/tc.2015.2456015","title":"DARE: A Deduplication-Aware Resemblance Detection and Elimination Scheme for Data Reduction with Low Overheads","display_name":"DARE: A Deduplication-Aware Resemblance Detection and Elimination Scheme for Data Reduction with Low Overheads","publication_year":2015,"publication_date":"2015-07-13","ids":{"openalex":"https://openalex.org/W2346147088","doi":"https://doi.org/10.1109/tc.2015.2456015","mag":"2346147088"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2015.2456015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2015.2456015","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Computers","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/A5050928208","display_name":"Wen Xia","orcid":"https://orcid.org/0000-0003-4093-6391"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"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":true,"raw_author_name":"Wen Xia","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, HuBei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, HuBei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285749","display_name":"Hong Jiang","orcid":"https://orcid.org/0000-0002-1477-9751"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nebraska-Lincoln, 217 Schorr Center, 1101 T Street, Lincoln, NE"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nebraska-Lincoln, 217 Schorr Center, 1101 T Street, Lincoln, NE","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057421680","display_name":"Dan Feng","orcid":"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"]},{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Feng","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, HuBei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, HuBei, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100777330","display_name":"Lei Tian","orcid":"https://orcid.org/0000-0001-5449-3232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Tian","raw_affiliation_strings":["Tintri, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"Tintri, Mountain View, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050928208"],"corresponding_institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":15.7542,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98841867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"65","issue":"6","first_page":"1692","last_page":"1705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9990000128746033,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9990000128746033,"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":0.9986000061035156,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9803000092506409,"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/data-deduplication","display_name":"Data deduplication","score":0.9400222897529602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8404636383056641},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.775815486907959},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7025874257087708},{"id":"https://openalex.org/keywords/adjacency-list","display_name":"Adjacency list","score":0.5798435211181641},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.503736674785614},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4923163652420044},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47428351640701294},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.46440744400024414},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4575774371623993},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4293508529663086},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38961005210876465},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21606257557868958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15172231197357178},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14876505732536316},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09346926212310791},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09067091345787048}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9400222897529602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8404636383056641},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.775815486907959},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7025874257087708},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.5798435211181641},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.503736674785614},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4923163652420044},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47428351640701294},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.46440744400024414},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4575774371623993},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4293508529663086},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38961005210876465},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21606257557868958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15172231197357178},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14876505732536316},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09346926212310791},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09067091345787048},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2015.2456015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2015.2456015","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4521535353","display_name":null,"funder_award_id":"2014QNRC019","funder_id":"https://openalex.org/F4320321760","funder_display_name":"Henan University of Science and Technology"},{"id":"https://openalex.org/G4635607277","display_name":null,"funder_award_id":"CNS-111660","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5099833248","display_name":null,"funder_award_id":"61232004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7218688228","display_name":null,"funder_award_id":"61173043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7480238338","display_name":null,"funder_award_id":"61025008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7591817966","display_name":null,"funder_award_id":"CNS-1016609","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G913812893","display_name":null,"funder_award_id":"61303046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320321760","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W22807665","https://openalex.org/W24740120","https://openalex.org/W69510097","https://openalex.org/W89823361","https://openalex.org/W120798314","https://openalex.org/W125480971","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1437397736","https://openalex.org/W1474119323","https://openalex.org/W1521407587","https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1614703486","https://openalex.org/W1856507064","https://openalex.org/W1929726975","https://openalex.org/W1947728686","https://openalex.org/W1969126835","https://openalex.org/W1985229168","https://openalex.org/W1997349095","https://openalex.org/W1998817683","https://openalex.org/W2005611725","https://openalex.org/W2029673812","https://openalex.org/W2053449578","https://openalex.org/W2056980397","https://openalex.org/W2071417930","https://openalex.org/W2073370301","https://openalex.org/W2107200720","https://openalex.org/W2110322986","https://openalex.org/W2110824055","https://openalex.org/W2128593562","https://openalex.org/W2132069633","https://openalex.org/W2132627996","https://openalex.org/W2134792144","https://openalex.org/W2135050683","https://openalex.org/W2138900633","https://openalex.org/W2146889157","https://openalex.org/W2148885851","https://openalex.org/W2156719566","https://openalex.org/W2216311525","https://openalex.org/W2281363974","https://openalex.org/W2583349018","https://openalex.org/W6600884019","https://openalex.org/W6601060166","https://openalex.org/W6602837329","https://openalex.org/W6603735688","https://openalex.org/W6604953292","https://openalex.org/W6605032692","https://openalex.org/W6607453207","https://openalex.org/W6608138927","https://openalex.org/W6628275343","https://openalex.org/W6631269574","https://openalex.org/W6634463810","https://openalex.org/W6638808162","https://openalex.org/W6640146480","https://openalex.org/W6640739288","https://openalex.org/W6663785121","https://openalex.org/W6679252032","https://openalex.org/W6679804201","https://openalex.org/W6688535418","https://openalex.org/W6695688771"],"related_works":["https://openalex.org/W1437397736","https://openalex.org/W4285245558","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W4301155776","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W3156188733","https://openalex.org/W2348132657","https://openalex.org/W4293433953"],"abstract_inverted_index":{"Data":[0],"reduction":[1,36],"has":[2,21],"become":[3],"increasingly":[4],"important":[5],"in":[6,17,23,74,119],"storage":[7,79],"systems":[8],"due":[9],"to":[10,39,87,103],"the":[11,18,24,30,127,157,164,189,193],"explosive":[12],"growth":[13],"of":[14,29,156],"digital":[15],"data":[16,26,35,75,101,115],"world":[19],"that":[20,63,147],"ushered":[22],"big":[25],"era.":[27],"One":[28],"main":[31,82],"challenges":[32],"facing":[33],"large-scale":[34],"is":[37,86],"how":[38],"maximally":[40],"detect":[41],"and":[42,60,123,142,153,159,174,187],"eliminate":[43],"redundancy":[44,173],"at":[45],"very":[46],"low":[47],"overheads.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"DARE,":[54],"a":[55,89,120,176],"low-overhead":[56],"deduplication-aware":[57],"resemblance":[58,72,128,185],"detection":[59,73,129,186],"elimination":[61],"scheme":[62],"effectively":[64],"exploits":[65],"existing":[66,181],"duplicate-adjacency":[67,182],"information":[68,183],"for":[69,108,184,192],"highly":[70],"efficient":[71],"deduplication":[76,121],"based":[77,93,139],"backup/archiving":[78],"systems.":[80],"The":[81],"idea":[83],"behind":[84],"DARE":[85,148],"employ":[88],"scheme,":[90],"call":[91],"Duplicate-Adjacency":[92],"Resemblance":[94],"Detection":[95],"(DupAdj),":[96],"by":[97,131,163,179],"considering":[98],"any":[99],"two":[100],"chunks":[102,116],"be":[104],"similar":[105],"(i.e.,":[106],"candidates":[107],"delta":[109],"compression)":[110],"if":[111],"their":[112],"respective":[113],"adjacent":[114],"are":[117],"duplicate":[118],"system,":[122],"then":[124],"further":[125],"enhance":[126],"efficiency":[130],"an":[132],"improved":[133],"super-feature":[134,166,194],"approach.":[135,195],"Our":[136],"experimental":[137],"results":[138],"on":[140],"real-world":[141],"synthetic":[143],"backup":[144],"datasets":[145],"show":[146],"only":[149],"consumes":[150],"about":[151],"1/4":[152],"1/2":[154],"respectively":[155],"computation":[158],"indexing":[160],"overheads":[161],"required":[162],"traditional":[165],"approaches":[167],"while":[168],"detecting":[169],"2-10":[170],"percent":[171],"more":[172],"achieving":[175],"higher":[177],"throughput,":[178],"exploiting":[180],"finding":[188],"\u201csweet":[190],"spot\u201d":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
