{"id":"https://openalex.org/W4410250014","doi":"https://doi.org/10.1145/3735508","title":"Distributed Data Deduplication for Big Data: A Survey","display_name":"Distributed Data Deduplication for Big Data: A Survey","publication_year":2025,"publication_date":"2025-05-10","ids":{"openalex":"https://openalex.org/W4410250014","doi":"https://doi.org/10.1145/3735508"},"language":"en","primary_location":{"id":"doi:10.1145/3735508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735508","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"ACM Computing Surveys","raw_type":"journal-article"},"type":"review","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/A5069247489","display_name":"Yinjin Fu","orcid":"https://orcid.org/0000-0001-9107-1338"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinjin Fu","raw_affiliation_strings":["School of Cyber Science and Technology, Sun Yat-Sen University","School of Cyber Science and Technology, Sun Yat-Sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9107-1338","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-Sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Su","orcid":"https://orcid.org/0009-0000-7401-7233"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Su","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University","Sun Yat-Sen University,  Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-7401-7233","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-Sen University,  Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiahao Ning","orcid":"https://orcid.org/0009-0008-4981-7317"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Ning","raw_affiliation_strings":["School of Cyber Science and Technology, Sun Yat-Sen University","Sun Yat-Sen University,  Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-4981-7317","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-Sen University,  Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100510864","display_name":"Jian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["School of Cyber Science and Technology, Sun Yat-Sen University","Sun Yat-Sen University,  Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-1229-4546","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-Sen University,  Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University","Sun Yat-Sen University,  Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5315-3375","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-Sen University,  Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023506057","display_name":"Nong Xiao","orcid":"https://orcid.org/0000-0002-2166-977X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Xiao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University","Sun Yat-Sen University,  Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2166-977X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-Sen University,  Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069247489"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":5.8102,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95387601,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"58","issue":"3","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9994000196456909,"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":0.9994000196456909,"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":0.995199978351593,"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/T11478","display_name":"Caching and Content Delivery","score":0.9887999892234802,"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/data-deduplication","display_name":"Data deduplication","score":0.9068504571914673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8885915279388428},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5314998030662537},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.40876275300979614},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3397403359413147},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23049592971801758}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9068504571914673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8885915279388428},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5314998030662537},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40876275300979614},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3397403359413147},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23049592971801758}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3735508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735508","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1891631727","display_name":null,"funder_award_id":"2022YFB4500304","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7088822926","display_name":null,"funder_award_id":"62332021, 62461146204","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":133,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W26020480","https://openalex.org/W1418704970","https://openalex.org/W1516634968","https://openalex.org/W1523836018","https://openalex.org/W1526227463","https://openalex.org/W1542686980","https://openalex.org/W1545493325","https://openalex.org/W1553098517","https://openalex.org/W1675372141","https://openalex.org/W1963535513","https://openalex.org/W1967373117","https://openalex.org/W1969126835","https://openalex.org/W1969949656","https://openalex.org/W1975868314","https://openalex.org/W1979162731","https://openalex.org/W1988161332","https://openalex.org/W1996771666","https://openalex.org/W2004286258","https://openalex.org/W2004493170","https://openalex.org/W2010150514","https://openalex.org/W2016947394","https://openalex.org/W2020928798","https://openalex.org/W2027016098","https://openalex.org/W2028928922","https://openalex.org/W2033062224","https://openalex.org/W2045202139","https://openalex.org/W2047484077","https://openalex.org/W2050140640","https://openalex.org/W2055899630","https://openalex.org/W2056980397","https://openalex.org/W2063421119","https://openalex.org/W2067282435","https://openalex.org/W2070077528","https://openalex.org/W2073370301","https://openalex.org/W2075108022","https://openalex.org/W2077571738","https://openalex.org/W2082802755","https://openalex.org/W2088351633","https://openalex.org/W2100632211","https://openalex.org/W2103275940","https://openalex.org/W2104210894","https://openalex.org/W2107745473","https://openalex.org/W2110824055","https://openalex.org/W2111238480","https://openalex.org/W2113154035","https://openalex.org/W2123845384","https://openalex.org/W2126540423","https://openalex.org/W2129167380","https://openalex.org/W2130975798","https://openalex.org/W2131287008","https://openalex.org/W2133806194","https://openalex.org/W2133893097","https://openalex.org/W2138033199","https://openalex.org/W2142606934","https://openalex.org/W2157240622","https://openalex.org/W2157604883","https://openalex.org/W2157870327","https://openalex.org/W2162734706","https://openalex.org/W2165257856","https://openalex.org/W2214767746","https://openalex.org/W2288443673","https://openalex.org/W2289555345","https://openalex.org/W2290204549","https://openalex.org/W2343548694","https://openalex.org/W2345185127","https://openalex.org/W2475932436","https://openalex.org/W2481150113","https://openalex.org/W2512339778","https://openalex.org/W2513414733","https://openalex.org/W2540788271","https://openalex.org/W2583728456","https://openalex.org/W2603306480","https://openalex.org/W2621279243","https://openalex.org/W2734941459","https://openalex.org/W2751054914","https://openalex.org/W2752939837","https://openalex.org/W2780813414","https://openalex.org/W2788578295","https://openalex.org/W2789512909","https://openalex.org/W2792685735","https://openalex.org/W2799944323","https://openalex.org/W2800515890","https://openalex.org/W2810972659","https://openalex.org/W2858929329","https://openalex.org/W2903617882","https://openalex.org/W2904124380","https://openalex.org/W2904320757","https://openalex.org/W2911837627","https://openalex.org/W2912893741","https://openalex.org/W2915025126","https://openalex.org/W2963947431","https://openalex.org/W2982637157","https://openalex.org/W2986445348","https://openalex.org/W3018446257","https://openalex.org/W3036938873","https://openalex.org/W3038221855","https://openalex.org/W3041188391","https://openalex.org/W3094998779","https://openalex.org/W3102408035","https://openalex.org/W3114983673","https://openalex.org/W3123643475","https://openalex.org/W3170782232","https://openalex.org/W3173499193","https://openalex.org/W3174041641","https://openalex.org/W3176566624","https://openalex.org/W3215043440","https://openalex.org/W4205690218","https://openalex.org/W4225507060","https://openalex.org/W4230388729","https://openalex.org/W4285181595","https://openalex.org/W4285245558","https://openalex.org/W4287077924","https://openalex.org/W4298005108","https://openalex.org/W4312796475","https://openalex.org/W4312922745","https://openalex.org/W4316660797","https://openalex.org/W4316661034","https://openalex.org/W4318477538","https://openalex.org/W4321089583","https://openalex.org/W4360995120","https://openalex.org/W4387490814","https://openalex.org/W4388444425","https://openalex.org/W4389166743","https://openalex.org/W4390097713","https://openalex.org/W4390604572","https://openalex.org/W4390833467","https://openalex.org/W4395020705","https://openalex.org/W4398174366","https://openalex.org/W4400654804","https://openalex.org/W4401455073","https://openalex.org/W4408765631","https://openalex.org/W6884946747"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2731626691","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084"],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,65,76,79,99,111,115,139,151],"throughput":[3],"and":[4,31,51,74,101,109,142,149,154],"capacity":[5],"limitations":[6],"of":[7,67,82,103,114,145],"single-node":[8],"centralized":[9],"deduplication,":[10,85,148],"distributed":[11,83,117,132,146],"data":[12,21,38,48,69,84,87,91,95,118,133,147],"deduplication":[13,44,119,134],"has":[14],"become":[15],"a":[16,47],"popular":[17],"technology":[18],"in":[19,56,78],"big":[20,68],"management":[22],"to":[23,42],"save":[24],"more":[25],"storage":[26],"space,":[27],"enhance":[28],"I/O":[29],"performance,":[30],"improve":[32],"system":[33,112],"scalability.":[34],"It":[35],"includes":[36],"inter-node":[37],"assignment":[39],"from":[40],"clients":[41],"multiple":[43],"nodes":[45],"by":[46],"routing":[49],"scheme,":[50],"independent":[52],"intra-node":[53],"redundancy":[54],"suppression":[55],"individual":[57],"nodes.":[58],"In":[59],"this":[60],"article,":[61],"we":[62,72,122,137],"first":[63],"describe":[64],"background":[66],"deduplication.":[70],"Then":[71],"summarize":[73],"classify":[75],"state-of-the-art":[77],"key":[80],"techniques":[81],"including":[86],"partitioning,":[88],"chunk":[89],"fingerprinting,":[90],"routing,":[92],"index":[93],"lookup,":[94],"restoring,":[96],"garbage":[97],"collection,":[98],"security":[100],"reliability":[102],"deduplicated":[104],"data.":[105],"These":[106],"help":[107],"identify":[108],"understand":[110],"implementation":[113],"existing":[116],"methods.":[120],"Moreover,":[121],"present":[123],"some":[124],"representative":[125],"industrial":[126],"products":[127],"that":[128],"have":[129],"successfully":[130],"applied":[131],"technologies.":[135],"Finally,":[136],"discuss":[138],"main":[140],"challenges":[141],"industry":[143],"trend":[144],"outline":[150],"open":[152],"problems":[153],"its":[155],"future":[156],"research":[157],"directions.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}