{"id":"https://openalex.org/W4411403379","doi":"https://doi.org/10.1145/3725340","title":"Privacy and Accuracy-Aware AI/ML Model Deduplication","display_name":"Privacy and Accuracy-Aware AI/ML Model Deduplication","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411403379","doi":"https://doi.org/10.1145/3725340"},"language":"en","primary_location":{"id":"doi:10.1145/3725340","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725340","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3725340","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101909130","display_name":"Hong Guan","orcid":"https://orcid.org/0000-0003-2781-4242"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Guan","raw_affiliation_strings":["Arizona State University, Tempe, USA"],"raw_orcid":"https://orcid.org/0000-0003-2781-4242","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743046","display_name":"Lei Yu","orcid":"https://orcid.org/0000-0001-5968-0344"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yu","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, USA"],"raw_orcid":"https://orcid.org/0000-0001-5968-0344","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069847527","display_name":"Lixi Zhou","orcid":"https://orcid.org/0000-0001-8481-3292"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lixi Zhou","raw_affiliation_strings":["Arizona State University, Tempe, USA"],"raw_orcid":"https://orcid.org/0000-0001-8481-3292","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078394535","display_name":"Li Xiong","orcid":"https://orcid.org/0000-0001-7354-0428"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Xiong","raw_affiliation_strings":["Emory University, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0001-7354-0428","affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102955722","display_name":"Kanchan Chowdhury","orcid":"https://orcid.org/0009-0004-6528-9324"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanchan Chowdhury","raw_affiliation_strings":["Arizona State University, Tempe, USA"],"raw_orcid":"https://orcid.org/0009-0004-6528-9324","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008421819","display_name":"Lulu Xie","orcid":"https://orcid.org/0000-0001-8902-222X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lulu Xie","raw_affiliation_strings":["Arizona State University, Tempe, USA"],"raw_orcid":"https://orcid.org/0000-0001-8902-222X","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012621594","display_name":"Xusheng Xiao","orcid":"https://orcid.org/0000-0003-4797-4294"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xusheng Xiao","raw_affiliation_strings":["Arizona State University, Tempe, USA"],"raw_orcid":"https://orcid.org/0000-0003-4797-4294","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013735333","display_name":"Jia Zou","orcid":"https://orcid.org/0000-0001-9849-0711"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Zou","raw_affiliation_strings":["Arizona State University, Tempe, USA"],"raw_orcid":"https://orcid.org/0000-0001-9849-0711","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84240068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10237","display_name":"Cryptography and Data Security","score":0.9814000129699707,"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/computer-science","display_name":"Computer science","score":0.8601434230804443},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8100541830062866},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6850791573524475},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5185197591781616},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5065735578536987},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4730367362499237},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.42939573526382446},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42247137427330017},{"id":"https://openalex.org/keywords/private-information-retrieval","display_name":"Private information retrieval","score":0.41960498690605164},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4124307632446289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39202606678009033},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30493396520614624},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.18137943744659424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8601434230804443},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8100541830062866},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6850791573524475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5185197591781616},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5065735578536987},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4730367362499237},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.42939573526382446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42247137427330017},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.41960498690605164},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4124307632446289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39202606678009033},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30493396520614624},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18137943744659424},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"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:10.1145/3725340","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725340","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3725340","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725340","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G3581923794","display_name":null,"funder_award_id":"2144923 and 2431532","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7841657763","display_name":null,"funder_award_id":"17STQAC00001-07-00","funder_id":"https://openalex.org/F4320306110","funder_display_name":"U.S. Department of Homeland Security"}],"funders":[{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1559390933","https://openalex.org/W1834627138","https://openalex.org/W1964234041","https://openalex.org/W1986017822","https://openalex.org/W2021651899","https://openalex.org/W2022097286","https://openalex.org/W2032775418","https://openalex.org/W2051267297","https://openalex.org/W2062822390","https://openalex.org/W2067713319","https://openalex.org/W2070162726","https://openalex.org/W2096870293","https://openalex.org/W2109426455","https://openalex.org/W2111116800","https://openalex.org/W2146875405","https://openalex.org/W2150916025","https://openalex.org/W2158760370","https://openalex.org/W2162006472","https://openalex.org/W2194775991","https://openalex.org/W2251939518","https://openalex.org/W2272515049","https://openalex.org/W2340222647","https://openalex.org/W2473418344","https://openalex.org/W2492590231","https://openalex.org/W2535690855","https://openalex.org/W2547190417","https://openalex.org/W2566913073","https://openalex.org/W2604566160","https://openalex.org/W2798535736","https://openalex.org/W2948176562","https://openalex.org/W2962895657","https://openalex.org/W2963506795","https://openalex.org/W2963846996","https://openalex.org/W2982157693","https://openalex.org/W3008924290","https://openalex.org/W3033567383","https://openalex.org/W3034368386","https://openalex.org/W3035168593","https://openalex.org/W3138154797","https://openalex.org/W3138815606","https://openalex.org/W3145740377","https://openalex.org/W3146259567","https://openalex.org/W3165312848","https://openalex.org/W3197468999","https://openalex.org/W4205228770","https://openalex.org/W4206688953","https://openalex.org/W4249672879","https://openalex.org/W4254788633","https://openalex.org/W4286447321","https://openalex.org/W4287828539","https://openalex.org/W4293166090","https://openalex.org/W4294904057","https://openalex.org/W4380925616","https://openalex.org/W4388080294","https://openalex.org/W4389609557","https://openalex.org/W4391054875","https://openalex.org/W6600336842","https://openalex.org/W6635444389","https://openalex.org/W6720608135","https://openalex.org/W6774302960","https://openalex.org/W6966782918"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2955229517","https://openalex.org/W2966297898","https://openalex.org/W2596305496"],"abstract_inverted_index":{"With":[0],"the":[1,33,97,126,133,147,181,187,201,228],"growing":[2],"adoption":[3],"of":[4,52,96,109,128,230],"privacy-preserving":[5],"machine":[6],"learning":[7],"algorithms,":[8],"such":[9],"as":[10],"Differentially":[11],"Private":[12],"Stochastic":[13],"Gradient":[14],"Descent":[15],"(DP-SGD),":[16],"training":[17],"or":[18],"fine-tuning":[19],"models":[20,36,54,115,131,159,162,210,214],"on":[21],"private":[22,192],"datasets":[23],"has":[24,30,102],"become":[25],"increasingly":[26],"prevalent.":[27],"This":[28],"shift":[29],"led":[31],"to":[32,44,83,106,120,145,154,160,163,185,196,206,222,227],"need":[34],"for":[35,112,132,208],"offering":[37],"varying":[38],"privacy":[39,110,167,188],"guarantees":[40],"and":[41,66,80,86,90,116,136,141,156,166,179,215],"utility":[42],"levels":[43],"satisfy":[45],"diverse":[46],"user":[47],"requirements.":[48],"Managing":[49],"numerous":[50],"versions":[51],"large":[53,212],"introduces":[55],"significant":[56],"operational":[57],"challenges,":[58],"including":[59],"increased":[60],"inference":[61,88,224],"latency,":[62],"higher":[63],"resource":[64],"consumption,":[65],"elevated":[67],"costs.":[68,168],"Model":[69],"deduplication":[70,100,143],"is":[71],"a":[72,138,151,171],"technique":[73],"widely":[74],"used":[75],"by":[76,204],"many":[77],"model":[78,91,99],"serving":[79],"database":[81],"systems":[82],"support":[84],"high-performance":[85],"low-cost":[87],"queries":[89],"diagnosis":[92],"queries.":[93],"However,":[94],"none":[95],"existing":[98],"works":[101],"considered":[103],"privacy,":[104],"leading":[105],"unbounded":[107],"aggregation":[108],"costs":[111,189],"certain":[113],"deduplicated":[114],"inefficiencies":[117],"when":[118],"applied":[119],"deduplicate":[121],"DP-trained":[122,130],"models.":[123],"We":[124,149,218],"formalize":[125],"problem":[127],"deduplicating":[129,170],"first":[134],"time":[135],"propose":[137],"novel":[139],"privacy-":[140],"accuracy-aware":[142],"mechanism":[144],"address":[146],"problem.":[148],"developed":[150],"greedy":[152],"strategy":[153],"select":[155],"assign":[157],"base":[158],"target":[161,172],"minimize":[164],"storage":[165],"When":[169],"model,":[173],"we":[174],"dynamically":[175],"schedule":[176],"accuracy":[177],"validations":[178],"apply":[180],"Sparse":[182],"Vector":[183],"Technique":[184],"reduce":[186],"associated":[190],"with":[191],"validation":[193],"data.":[194],"Compared":[195],"baselines,":[197],"our":[198],"approach":[199],"improved":[200],"compression":[202],"ratio":[203],"up":[205,221],"35\u00d7":[207],"individual":[209],"(including":[211],"language":[213],"vision":[216],"transformers).":[217],"also":[219],"observed":[220],"43\u00d7":[223],"speedup":[225],"due":[226],"reduction":[229],"I/O":[231],"operations.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}