{"id":"https://openalex.org/W2083695892","doi":"https://doi.org/10.1109/p2p.2010.5570004","title":"PeerDedupe: Insights into the Peer-Assisted Sampling Deduplication","display_name":"PeerDedupe: Insights into the Peer-Assisted Sampling Deduplication","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2083695892","doi":"https://doi.org/10.1109/p2p.2010.5570004","mag":"2083695892"},"language":"en","primary_location":{"id":"doi:10.1109/p2p.2010.5570004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/p2p.2010.5570004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Tenth International Conference on Peer-to-Peer Computing (P2P)","raw_type":"proceedings-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/A5101653566","display_name":"Yanan Xing","orcid":"https://orcid.org/0000-0002-1157-3686"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Y. Xing","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069034933","display_name":"Z. Li","orcid":"https://orcid.org/0009-0001-9354-1708"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Z. Li","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052957076","display_name":"Yafei Dai","orcid":"https://orcid.org/0000-0002-7738-5258"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Y. Dai","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101653566"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.8596,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86503949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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":0.9983999729156494,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.990473747253418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7855883836746216},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4934457838535309},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.48146572709083557},{"id":"https://openalex.org/keywords/peer-to-peer","display_name":"Peer-to-peer","score":0.46132200956344604},{"id":"https://openalex.org/keywords/gene-duplication","display_name":"Gene duplication","score":0.4163690209388733},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3200494050979614},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2972623109817505},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07095035910606384}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.990473747253418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7855883836746216},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4934457838535309},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.48146572709083557},{"id":"https://openalex.org/C534932454","wikidata":"https://www.wikidata.org/wiki/Q161410","display_name":"Peer-to-peer","level":2,"score":0.46132200956344604},{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.4163690209388733},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3200494050979614},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2972623109817505},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07095035910606384},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/p2p.2010.5570004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/p2p.2010.5570004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Tenth International Conference on Peer-to-Peer Computing (P2P)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.5839","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.5839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.greenorbs.org/people/lzh/papers/%5BP2P%2710%5D%20PeerDedupe.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1576397915","https://openalex.org/W1847423537","https://openalex.org/W1963535513","https://openalex.org/W1969126835","https://openalex.org/W1974757757","https://openalex.org/W1975868314","https://openalex.org/W1990313671","https://openalex.org/W2004286258","https://openalex.org/W2047484077","https://openalex.org/W2056980397","https://openalex.org/W2081193615","https://openalex.org/W2109572691","https://openalex.org/W2131566399","https://openalex.org/W2132069633","https://openalex.org/W2148885851","https://openalex.org/W2267182614","https://openalex.org/W2745750801","https://openalex.org/W6602837329","https://openalex.org/W6608138927","https://openalex.org/W6629455298","https://openalex.org/W6634463810","https://openalex.org/W6638825795","https://openalex.org/W6682205557","https://openalex.org/W6693092141"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2074021203","https://openalex.org/W2144348063","https://openalex.org/W4296125805","https://openalex.org/W2179326652"],"abstract_inverted_index":{"As":[0],"the":[1,24,27,43,69,77,86,137],"digital":[2],"data":[3,11,20],"rapidly":[4],"inflates":[5],"to":[6],"a":[7,36,82,102],"world-wide":[8],"storage":[9],"crisis,":[10],"deduplication":[12,30,44,106],"is":[13,49],"showing":[14],"its":[15],"increasingly":[16],"prominent":[17],"function":[18],"in":[19],"storage.":[21],"Driven":[22],"by":[23],"problems":[25],"behind":[26],"mainstream":[28],"server-side":[29],"schemes,":[31],"recently":[32],"there":[33],"has":[34],"been":[35],"tendency":[37],"of":[38,85],"introducing":[39],"peer-assisted":[40,70,104],"methods":[41],"into":[42],"systems.":[45],"However,":[46],"this":[47,60],"topic":[48],"still":[50],"quite":[51],"vague":[52],"at":[53],"present":[54],"and":[55,65,89,128],"lacks":[56],"thorough":[57],"research.":[58],"In":[59],"paper,":[61],"we":[62,74,99],"conduct":[63],"in-depth":[64],"quantitative":[66],"investigation":[67],"on":[68,96],"deduplication.":[71],"Through":[72],"measurements":[73],"observe":[75],"that":[76,110],"inter-peer":[78],"duplication":[79,116],"accounts":[80],"for":[81],"large":[83],"proportion":[84],"total":[87],"duplication,":[88],"exhibits":[90],"strong":[91],"peer":[92,119],"locality.":[93],"Then":[94],"based":[95],"our":[97],"observations,":[98],"propose":[100],"PeerDedupe,":[101],"novel":[103],"sampling":[105],"approach.":[107],"Experiments":[108],"show":[109],"PeerDedupe":[111],"can":[112],"remove":[113],"over":[114],"98%":[115],"with":[117,121],"each":[118],"coordinating":[120],"no":[122],"more":[123],"than":[124,136],"5":[125],"other":[126],"peers,":[127],"it":[129],"requires":[130],"much":[131],"less":[132],"server":[133],"RAM":[134],"usage":[135],"existing":[138],"works.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
