{"id":"https://openalex.org/W4214896642","doi":"https://doi.org/10.1109/tnse.2022.3155357","title":"Pushing Collaborative Data Deduplication to the Network Edge: An Optimization Framework and System Design","display_name":"Pushing Collaborative Data Deduplication to the Network Edge: An Optimization Framework and System Design","publication_year":2022,"publication_date":"2022-03-01","ids":{"openalex":"https://openalex.org/W4214896642","doi":"https://doi.org/10.1109/tnse.2022.3155357"},"language":"en","primary_location":{"id":"doi:10.1109/tnse.2022.3155357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2022.3155357","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Network Science and Engineering","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/A5103047399","display_name":"Shijing Li","orcid":"https://orcid.org/0000-0002-0085-7106"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shijing Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0002-0085-7106","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018464968","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0003-3010-8090"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0003-3010-8090","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033872928","display_name":"Bharath Balasubramanian","orcid":"https://orcid.org/0000-0003-2002-2349"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bharath Balasubramanian","raw_affiliation_strings":["AT&amp;T Labs Research, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2002-2349","affiliations":[{"raw_affiliation_string":"AT&amp;T Labs Research, Atlanta, GA, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040758822","display_name":"Hee Won Lee","orcid":"https://orcid.org/0000-0001-8367-7575"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hee Won Lee","raw_affiliation_strings":["AT&amp;T Labs Research, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs Research, Atlanta, GA, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017417851","display_name":"Moo-Ryong Ra","orcid":"https://orcid.org/0000-0003-3336-2166"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moo-Ryong Ra","raw_affiliation_strings":["AT&amp;T Labs Research, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3336-2166","affiliations":[{"raw_affiliation_string":"AT&amp;T Labs Research, Atlanta, GA, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111575718","display_name":"Rajesh Panta","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajesh Krishna Panta","raw_affiliation_strings":["AT&amp;T Labs Research, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs Research, Atlanta, GA, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9982,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7629206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"9","issue":"4","first_page":"2110","last_page":"2122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9954000115394592,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9954000115394592,"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":0.9939000010490417,"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/T11478","display_name":"Caching and Content Delivery","score":0.9865999817848206,"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":0.9194556474685669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7653321027755737},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6505702137947083},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5327831506729126},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4439306855201721},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4414919316768646},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43417078256607056},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4220539927482605},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21069258451461792},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16363367438316345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11352008581161499}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9194556474685669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653321027755737},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6505702137947083},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5327831506729126},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4439306855201721},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4414919316768646},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43417078256607056},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4220539927482605},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21069258451461792},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16363367438316345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11352008581161499},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnse.2022.3155357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2022.3155357","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Network Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G6297984428","display_name":null,"funder_award_id":"1618628","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W26020480","https://openalex.org/W1896689416","https://openalex.org/W1969126835","https://openalex.org/W1978971465","https://openalex.org/W1996149237","https://openalex.org/W1997349095","https://openalex.org/W1998817683","https://openalex.org/W2022966373","https://openalex.org/W2047484077","https://openalex.org/W2105557521","https://openalex.org/W2129412326","https://openalex.org/W2133893097","https://openalex.org/W2143853136","https://openalex.org/W2153158407","https://openalex.org/W2475932436","https://openalex.org/W2734855181","https://openalex.org/W2741464441","https://openalex.org/W2806197565","https://openalex.org/W2885231984","https://openalex.org/W2982637157","https://openalex.org/W6600228218","https://openalex.org/W6601060166","https://openalex.org/W6608138927","https://openalex.org/W6629956336","https://openalex.org/W6631269574","https://openalex.org/W6639507657","https://openalex.org/W6695688771","https://openalex.org/W6742083786"],"related_works":["https://openalex.org/W4313339048","https://openalex.org/W3176734149","https://openalex.org/W3201779876","https://openalex.org/W3113627641","https://openalex.org/W3191964704","https://openalex.org/W2918879532","https://openalex.org/W3083220997","https://openalex.org/W2885461866","https://openalex.org/W3162654428","https://openalex.org/W2901937988"],"abstract_inverted_index":{"Edge":[0],"computing":[1,6,62],"has":[2],"become":[3],"a":[4,28,69,101,108,130,156,200,211,218],"new":[5,29],"paradigm":[7],"with":[8,135,148,163,190],"explosive":[9],"growth":[10],"in":[11,52,68,184,210,250],"recent":[12],"years.":[13],"We":[14,154],"consider":[15],"the":[16,23,38,45,66,72,93,127,144,253,265],"problem":[17,121,162,178],"of":[18,48,129,174,252],"pushing":[19],"data":[20,54,138],"deduplication":[21,34,102,114,234],"to":[22,43,55,181,198,258],"network":[24,39,150,160],"edge":[25,40,53,67,73,79,94,133,146,175,208],"and":[26,50,85,112,125,159,171,195,217,240],"propose":[27],"framework":[30,189],"for":[31],"distributed":[32,61,109],"edge-facilitated":[33],"(EF-dedup).":[35],"Deduplication":[36],"at":[37,221],"allows":[41],"us":[42],"exploit":[44],"high":[46],"degree":[47],"geographic-":[49],"temporal-correlation":[51],"achieve":[56,199],"space":[57,84],"efficiency.":[58],"By":[59],"leveraging":[60],"power":[63],"available":[64],"on":[65,207],"collaborative":[70,98],"fashion,":[71],"nodes":[74,95,134,209],"can":[75],"effectively":[76],"suppress":[77],"duplicated":[78],"data,":[80],"consuming":[81],"considerably":[82],"less":[83],"WAN":[86],"bandwidth.":[87],"To":[88],"this":[89,119],"end,":[90],"we":[91],"partition":[92],"into":[96],"disjoint":[97],"clusters,":[99],"maintain":[100],"index":[103],"structure":[104],"across":[105],"them":[106],"using":[107],"key-value":[110],"store":[111],"perform":[113],"within":[115,143],"those":[116],"clusters.":[117],"However,":[118],"partitioning":[120,170,173],"is":[122,179,193,196],"very":[123],"challenging":[124],"requires":[126],"optimization":[128,161,188],"novel":[131],"tradeoff:":[132],"highly":[136],"correlated":[137],"may":[139],"not":[140],"always":[141],"be":[142,182],"same":[145],"cloud,":[147],"non-trivial":[149],"cost":[151,249],"among":[152],"them.":[153],"formulate":[155],"joint":[157],"storage":[158],"different":[164],"design":[165],"objectives,":[166],"such":[167],"as":[168,256],"arbitrary":[169],"balanced":[172],"nodes.":[176],"The":[177],"shown":[180],"NP-Hard":[183],"general.":[185],"Then,":[186],"an":[187],"efficient":[191],"algorithms":[192],"developed":[194],"proven":[197],"closed-form":[201],"competitive":[202],"ratio.":[203],"Our":[204],"experiments,":[205],"performed":[206],"corporate":[212],"lab":[213],"<sup":[214],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[215,229,244],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[216],"central":[219],"cloud":[220],"AWS,":[222],"demonstrate":[223],"that":[224,260],"EF-dedup":[225],"achieves":[226,241],"67.4":[227],"<inline-formula":[228,243],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[230,245],"notation=\"LaTeX\">$\\sim$</tex-math></inline-formula>":[231],"133.7%":[232],"better":[233],"throughput":[235],"than":[236],"sole":[237],"cloud-based":[238],"techniques":[239],"20.0-62.6":[242],"notation=\"LaTeX\">$\\%$</tex-math></inline-formula>":[246],"lesser":[247],"aggregate":[248],"terms":[251],"network-storage":[254],"trade-off":[255],"compared":[257],"approaches":[259],"solely":[261],"favor":[262],"one":[263],"over":[264],"other.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}