{"id":"https://openalex.org/W4400277649","doi":"https://doi.org/10.1109/icoin59985.2024.10572208","title":"Personalized Federated Learning via Deviation Tracking Representation Learning","display_name":"Personalized Federated Learning via Deviation Tracking Representation Learning","publication_year":2024,"publication_date":"2024-01-17","ids":{"openalex":"https://openalex.org/W4400277649","doi":"https://doi.org/10.1109/icoin59985.2024.10572208"},"language":"en","primary_location":{"id":"doi:10.1109/icoin59985.2024.10572208","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icoin59985.2024.10572208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Information Networking (ICOIN)","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/A5058678382","display_name":"Jae\u2010Won Jang","orcid":"https://orcid.org/0000-0003-3540-530X"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewon Jang","raw_affiliation_strings":["Soongsil University,Computer Science and Engineering,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soongsil University,Computer Science and Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088745395","display_name":"Bong Jun Choi","orcid":"https://orcid.org/0000-0002-6550-749X"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bong Jun Choi","raw_affiliation_strings":["Soongsil University,Computer Science and Engineering,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soongsil University,Computer Science and Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I141371507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141371507"],"apc_list":null,"apc_paid":null,"fwci":0.2986,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62055679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"III","issue":null,"first_page":"762","last_page":"766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9948999881744385,"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":0.9948999881744385,"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":0.7834118604660034},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5897045731544495},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.531064510345459},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46991339325904846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4479043185710907},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4082286059856415},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3396109342575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7834118604660034},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5897045731544495},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.531064510345459},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46991339325904846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4479043185710907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4082286059856415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3396109342575073},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icoin59985.2024.10572208","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icoin59985.2024.10572208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Information Networking (ICOIN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4300000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2963819344","https://openalex.org/W2990789643","https://openalex.org/W3099314130","https://openalex.org/W3168269241","https://openalex.org/W4285071899","https://openalex.org/W4287906413","https://openalex.org/W4294646197","https://openalex.org/W6728757088","https://openalex.org/W6736057607","https://openalex.org/W6750254146","https://openalex.org/W6759238902","https://openalex.org/W6770590064","https://openalex.org/W6772318479","https://openalex.org/W6773817997","https://openalex.org/W6784336702","https://openalex.org/W6791102956","https://openalex.org/W6796504275","https://openalex.org/W6803975782","https://openalex.org/W6839362776"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W2023861399","https://openalex.org/W2062195135","https://openalex.org/W2730915376","https://openalex.org/W2626306547","https://openalex.org/W2021396365","https://openalex.org/W2394134009","https://openalex.org/W2119515433","https://openalex.org/W2795079307","https://openalex.org/W2961085424"],"abstract_inverted_index":{"Federated":[0],"learning":[1,44],"preserves":[2],"privacy":[3],"by":[4],"decentralized":[5],"training":[6,109,122,176],"of":[7,34,149,173,202,211],"individual":[8,66],"client":[9,113],"devices,":[10],"ensuring":[11],"only":[12,105],"model":[13,45,161],"weights":[14],"are":[15],"shared":[16,54],"centrally.":[17],"However,":[18],"the":[19,42,51,58,61,73,84,100,127,138,146,159,164,171],"data":[20,92,114],"heterogeneity":[21],"across":[22,152],"clients":[23,165],"presents":[24],"challenges.":[25],"This":[26,94,154],"paper":[27],"focuses":[28],"on":[29,144,177],"representation":[30,43],"learning,":[31],"a":[32,130,134,182,199,209],"variant":[33],"personalized":[35],"federated":[36],"learning.":[37],"According":[38],"to":[39,57,65,91,110,136,157,185],"various":[40],"studies,":[41],"can":[46,95,123],"be":[47],"divided":[48],"into":[49],"two:":[50],"base":[52,74,121,175],"layer,":[53,63],"and":[55,60,79,99,180,193],"updated":[56],"server,":[59],"head":[62,85,101],"localized":[64],"clients.":[67,153],"The":[68,168],"novel":[69,183],"approach":[70,184],"exclusively":[71],"utilizes":[72],"layer":[75,86,102],"for":[76,106,141,162],"both":[77],"local":[78],"global":[80,160],"training,":[81],"arguing":[82],"that":[83,119],"might":[87],"introduce":[88],"noise":[89],"due":[90],"heterogeneity.":[93],"potentially":[96],"affect":[97],"accuracy,":[98],"is":[103],"used":[104],"fine-tuning":[107,142,178,188],"after":[108],"capture":[111],"unique":[112],"characteristics.":[115],"Here,":[116],"we":[117,132,197],"observed":[118],"prolonged":[120],"diminish":[124],"accuracy":[125,151,179,201],"in":[126],"post-fine-tuning.":[128],"As":[129],"countermeasure,":[131],"proposed":[133],"method":[135],"determine":[137],"best":[139],"round":[140],"based":[143],"monitoring":[145],"standard":[147],"deviation":[148],"test":[150],"strategy":[155],"aims":[156],"generalize":[158],"all":[163],"before":[166],"fine-tuning.":[167],"study":[169],"highlights":[170],"downside":[172],"excessive":[174],"introduces":[181],"pinpoint":[186],"optimal":[187],"moments,":[189],"thereby":[190],"minimizing":[191],"computational":[192],"communication":[194,213],"overheads.":[195],"Similarly,":[196],"achieved":[198],"better":[200],"53.6%":[203],"than":[204],"other":[205],"approaches":[206],"while":[207],"there\u2019s":[208],"trade-off":[210],"minute":[212],"round.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}