{"id":"https://openalex.org/W4283359875","doi":"https://doi.org/10.1145/3512527.3531372","title":"FedNKD: A Dependable Federated Learning Using Fine-tuned Random Noise and Knowledge Distillation","display_name":"FedNKD: A Dependable Federated Learning Using Fine-tuned Random Noise and Knowledge Distillation","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283359875","doi":"https://doi.org/10.1145/3512527.3531372"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041039873","display_name":"Shaoxiong Zhu","orcid":"https://orcid.org/0000-0001-6046-1018"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxiong Zhu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406584","display_name":"Qi Qi","orcid":"https://orcid.org/0000-0003-0829-4624"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Qi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076969590","display_name":"Zirui Zhuang","orcid":"https://orcid.org/0000-0003-3345-1732"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zirui Zhuang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432460","display_name":"Jingyu Wang","orcid":"https://orcid.org/0000-0002-2182-2228"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008194128","display_name":"Haifeng Sun","orcid":"https://orcid.org/0000-0003-3072-7422"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Sun","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055685073","display_name":"Jianxin Liao","orcid":"https://orcid.org/0000-0003-1486-0573"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Liao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.6748,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68647949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"193"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9872999787330627,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9811000227928162,"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":0.8797097206115723},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6574851274490356},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5718163251876831},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49457451701164246},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4816690683364868},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4736936092376709},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4617566764354706},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.44570058584213257},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44543036818504333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4410489499568939},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.420022189617157},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.360387921333313},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3352360725402832},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.26907438039779663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8797097206115723},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6574851274490356},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5718163251876831},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49457451701164246},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4816690683364868},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4736936092376709},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4617566764354706},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.44570058584213257},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44543036818504333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4410489499568939},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.420022189617157},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.360387921333313},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3352360725402832},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26907438039779663},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G940957183","display_name":null,"funder_award_id":"62101064, 62171057, 62071067, 62001054","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2038752770","https://openalex.org/W2560674852","https://openalex.org/W2605800822","https://openalex.org/W2912213068","https://openalex.org/W2930926105","https://openalex.org/W2963140444","https://openalex.org/W2963318081","https://openalex.org/W2989289980","https://openalex.org/W2995022099","https://openalex.org/W2997006708","https://openalex.org/W3015636663","https://openalex.org/W3032967711","https://openalex.org/W3033500707","https://openalex.org/W3034067152","https://openalex.org/W3035321581","https://openalex.org/W3082520796","https://openalex.org/W3091870957","https://openalex.org/W3103245149","https://openalex.org/W3103557498","https://openalex.org/W3196899058","https://openalex.org/W3197438362"],"related_works":["https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3193043704","https://openalex.org/W3171520305","https://openalex.org/W1924178503","https://openalex.org/W3161989282","https://openalex.org/W3109499659","https://openalex.org/W4382315317","https://openalex.org/W2966641257","https://openalex.org/W3186268266"],"abstract_inverted_index":{"Multimedia":[0],"retrieval":[1,49],"models":[2],"need":[3,35],"the":[4,27,53,58,63,71,96,123,154,181,185,197],"ability":[5],"to":[6,40,47,61,67,78,84,119,152,195],"extract":[7],"useful":[8],"information":[9],"from":[10,81],"large-scale":[11],"data":[12,39,56,59,80,99,128],"for":[13],"clients.":[14],"As":[15],"an":[16],"important":[17],"part":[18],"of":[19,31,38,55,98,143,173,184],"multimedia":[20,32,48],"retrieval,":[21],"image":[22,43],"classification":[23,44],"model":[24,45,64,87,111],"directly":[25],"affects":[26],"efficiency":[28],"and":[29,137],"effect":[30],"retrieval.":[33],"We":[34],"a":[36,42,109,149,161],"lot":[37],"train":[41,62,85],"applied":[46],"task.":[50],"However,":[51],"with":[52,112,126],"protection":[54],"privacy,":[57],"used":[60],"often":[65],"needs":[66],"be":[68],"kept":[69],"on":[70],"client":[72,145],"side.":[73],"Federated":[74],"learning":[75,93,118],"is":[76,94,146,164],"proposed":[77],"use":[79,191],"all":[82],"clients":[83,102],"one":[86],"while":[88,200],"protecting":[89,201],"privacy.":[90,203],"When":[91],"federated":[92,117],"applied,":[95],"distribution":[97],"across":[100],"different":[101],"varies":[103],"greatly.":[104],"Disregarding":[105],"this":[106,192],"problem":[107],"yields":[108],"final":[110],"unstable":[113],"performance.":[114],"To":[115],"enable":[116],"work":[120],"dependably":[121],"in":[122,216],"real":[124,186],"world":[125],"complex":[127],"environments,":[129],"we":[130,189],"propose":[131],"FedNKD,":[132],"which":[133],"utilizes":[134],"knowledge":[135,142,198],"distillation":[136,199],"random":[138,168],"noise.":[139],"The":[140,176],"superior":[141],"each":[144],"distilled":[147],"into":[148],"central":[150],"server":[151],"mitigate":[153],"instablity":[155],"caused":[156],"by":[157,166,213],"Non-IID":[158],"data.":[159,187],"Importantly,":[160],"synthetic":[162,177,193],"dataset":[163,178,194],"created":[165],"some":[167],"noise":[169],"through":[170],"back":[171],"propagation":[172],"neural":[174],"networks.":[175],"will":[179,190],"contain":[180],"abstract":[182],"features":[183],"Then":[188],"realize":[196],"users'":[202],"In":[204],"our":[205],"experimental":[206],"scenarios,":[207],"FedNKD":[208],"outperforms":[209],"existing":[210],"representative":[211],"algorithms":[212],"about":[214],"1.5%":[215],"accuracy.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}