{"id":"https://openalex.org/W4296604473","doi":"https://doi.org/10.1145/3523227.3546769","title":"EANA: Reducing Privacy Risk on Large-scale Recommendation Models","display_name":"EANA: Reducing Privacy Risk on Large-scale Recommendation Models","publication_year":2022,"publication_date":"2022-09-13","ids":{"openalex":"https://openalex.org/W4296604473","doi":"https://doi.org/10.1145/3523227.3546769"},"language":"en","primary_location":{"id":"doi:10.1145/3523227.3546769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546769","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546769","source":null,"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 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546769","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001684158","display_name":"Lin Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lin Ning","raw_affiliation_strings":["Google Research, United States"],"affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078367630","display_name":"Steve Chien","orcid":"https://orcid.org/0000-0003-1023-9480"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Chien","raw_affiliation_strings":["Google Research, United States"],"affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731559","display_name":"Shuang Song","orcid":"https://orcid.org/0009-0005-9710-7748"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Song","raw_affiliation_strings":["Google Research, United States"],"affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360828","display_name":"Mei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei Chen","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031865684","display_name":"Yunqi Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunqi Xue","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039141224","display_name":"Devora Berlowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devora Berlowitz","raw_affiliation_strings":["Google Research, United States"],"affiliations":[{"raw_affiliation_string":"Google Research, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001684158"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.7957,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76795263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"399","last_page":"407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9775999784469604,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9350000023841858,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8577258586883545},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8018953800201416},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7369590997695923},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7246758341789246},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6512320637702942},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6433064937591553},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6073986887931824},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48812898993492126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46976304054260254},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4484732151031494},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.445947527885437},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44011980295181274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42954808473587036},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.40931302309036255},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38121217489242554},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3524189591407776},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.24809202551841736},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0783219039440155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577258586883545},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8018953800201416},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7369590997695923},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7246758341789246},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6512320637702942},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6433064937591553},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6073986887931824},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48812898993492126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46976304054260254},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4484732151031494},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.445947527885437},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44011980295181274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42954808473587036},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40931302309036255},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38121217489242554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3524189591407776},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24809202551841736},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0783219039440155},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523227.3546769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546769","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546769","source":null,"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 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3523227.3546769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546769","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546769","source":null,"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 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296604473.pdf","grobid_xml":"https://content.openalex.org/works/W4296604473.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1557833142","https://openalex.org/W1873763122","https://openalex.org/W2026653933","https://openalex.org/W2101771965","https://openalex.org/W2219888463","https://openalex.org/W2473418344","https://openalex.org/W2512971201","https://openalex.org/W2594311007","https://openalex.org/W2809290718","https://openalex.org/W2963149412","https://openalex.org/W2963935003","https://openalex.org/W2964103964","https://openalex.org/W2970618241","https://openalex.org/W2987249037","https://openalex.org/W3001405476","https://openalex.org/W3012615001","https://openalex.org/W3080873247","https://openalex.org/W3081362488"],"related_works":["https://openalex.org/W2092530219","https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2081900870","https://openalex.org/W2105580438","https://openalex.org/W4388717445","https://openalex.org/W4287755480","https://openalex.org/W2785875001","https://openalex.org/W4285818394"],"abstract_inverted_index":{"Embedding-based":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"are":[5],"widely":[6],"used":[7],"in":[8,82],"large-scale":[9,47,103,150,175],"recommendation":[10],"systems.":[11],"Differentially-private":[12],"stochastic":[13],"gradient":[14],"descent":[15],"(DP-SGD)":[16],"provides":[17],"a":[18,73,83,102,148,174],"way":[19],"to":[20,43,46,51,69,95],"enable":[21],"personalized":[22],"experiences":[23],"while":[24,133],"preserving":[25],"user":[26],"privacy":[27,110,137,180],"by":[28,63,141,167],"injecting":[29],"noise":[30,61,92],"into":[31],"every":[32],"model":[33,131,153],"parameter":[34,80],"during":[35],"the":[36,60,97,109,142,164,171],"training":[37,55,86,101,125,165,172],"process.":[38],"However,":[39],"it":[40],"is":[41,157],"challenging":[42],"apply":[44],"DP-SGD":[45,64],"embedding-based":[48,104,176],"DNNs":[49],"due":[50],"its":[52],"effect":[53],"on":[54,147],"speed.":[56],"This":[57,88],"happens":[58],"because":[59],"added":[62],"causes":[65],"normally":[66],"sparse":[67],"gradients":[68],"become":[70],"dense,":[71],"introducing":[72],"large":[74],"communication":[75,98],"overhead":[76],"between":[77],"workers":[78],"and":[79,116,152,169],"servers":[81],"typical":[84],"distributed":[85],"framework.":[87],"paper":[89],"proposes":[90],"embedding-aware":[91],"addition":[93],"(EANA)":[94],"mitigate":[96],"overhead,":[99],"making":[100],"DNN":[105,177],"possible.":[106],"We":[107,122],"examine":[108],"benefit":[111],"of":[112,173],"EANA":[113,127,156],"both":[114],"analytically":[115],"empirically":[117],"using":[118],"secret":[119,143],"sharer":[120,144],"techniques.":[121],"demonstrate":[123],"that":[124,155],"with":[126,178],"can":[128],"achieve":[129],"reasonable":[130],"precision":[132],"providing":[134],"good":[135],"practical":[136],"protection":[138],"as":[139],"measured":[140],"tests.":[145],"Experiments":[146],"real-world,":[149],"dataset":[151],"show":[154],"much":[158],"faster":[159],"than":[160],"standard":[161],"DP-SGD,":[162],"improving":[163],"speed":[166],"54X":[168],"unblocking":[170],"reduced":[179],"risk.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}