{"id":"https://openalex.org/W4225399801","doi":"https://doi.org/10.1109/icme52920.2022.9860009","title":"FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation","display_name":"FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4225399801","doi":"https://doi.org/10.1109/icme52920.2022.9860009"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9860009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9860009","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5067088554","display_name":"Xinyi Shang","orcid":"https://orcid.org/0000-0003-2287-3366"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Shang","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015745132","display_name":"Yang Lu","orcid":"https://orcid.org/0000-0002-3497-9611"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038516431","display_name":"Yiu\u2010ming Cheung","orcid":"https://orcid.org/0000-0001-7629-4648"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiu-Ming Cheung","raw_affiliation_strings":["Hong Kong Baptist University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044594971","display_name":"Hanzi Wang","orcid":"https://orcid.org/0000-0002-6913-9786"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9763000011444092,"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":0.9564999938011169,"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":0.8040130734443665},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6173254251480103},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6127017140388489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5842524170875549},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5634253621101379},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5398925542831421},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5397660732269287},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5026404857635498},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48917677998542786},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3749460279941559},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0906810462474823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040130734443665},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6173254251480103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6127017140388489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5842524170875549},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5634253621101379},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5398925542831421},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5397660732269287},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5026404857635498},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48917677998542786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3749460279941559},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0906810462474823},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.1109/icme52920.2022.9860009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9860009","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G4523446381","display_name":null,"funder_award_id":"62002302,61872307,61672444,U21A20514,N_HKBU214/21","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5173272783","display_name":null,"funder_award_id":"2020J01005","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1534477342","https://openalex.org/W1821462560","https://openalex.org/W2117539524","https://openalex.org/W2118978333","https://openalex.org/W2807006176","https://openalex.org/W2947380870","https://openalex.org/W2970941190","https://openalex.org/W2972570881","https://openalex.org/W2995197345","https://openalex.org/W3021654819","https://openalex.org/W3034369284","https://openalex.org/W3035453001","https://openalex.org/W3038022836","https://openalex.org/W3041497966","https://openalex.org/W3042621011","https://openalex.org/W3043723611","https://openalex.org/W3102074914","https://openalex.org/W3118608800","https://openalex.org/W3122967774","https://openalex.org/W3166492421","https://openalex.org/W3166596953","https://openalex.org/W3170490848","https://openalex.org/W3176639943","https://openalex.org/W3206816884","https://openalex.org/W4318619660","https://openalex.org/W6638523607","https://openalex.org/W6728757088","https://openalex.org/W6752029299","https://openalex.org/W6759238902","https://openalex.org/W6763430915","https://openalex.org/W6764733053","https://openalex.org/W6768920361","https://openalex.org/W6780224944","https://openalex.org/W6780718248","https://openalex.org/W6781318954","https://openalex.org/W6782317661","https://openalex.org/W6785175213","https://openalex.org/W6787193878","https://openalex.org/W6802739845"],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2785900585","https://openalex.org/W3026162553","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W2609066826","https://openalex.org/W2810752900","https://openalex.org/W3186538219","https://openalex.org/W2365677836","https://openalex.org/W2767178685"],"abstract_inverted_index":{"Federated":[0,102],"learning":[1,10,95,172],"provides":[2],"a":[3,38,98,131,159],"privacy":[4],"guarantee":[5],"for":[6,32],"generating":[7],"good":[8],"deep":[9],"models":[11,125],"on":[12,53,127,153],"distributed":[13],"clients":[14],"with":[15,22,105,111,135,158,166],"different":[16],"kinds":[17],"of":[18,27,40,47,88,121,124,170],"data.":[19,129],"Nevertheless,":[20],"dealing":[21],"non-IID":[23,55,89,112,128,161],"data":[24,56,92],"is":[25,63,73,142,178],"one":[26],"the":[28,44,54,59,69,77,85,122,146,167],"most":[29],"challenging":[30],"problems":[31],"federated":[33,94,171],"learning.":[34,175],"Researchers":[35],"have":[36],"proposed":[37,143],"variety":[39],"methods":[41,169],"to":[42,118,144],"eliminate":[43],"negative":[45],"influence":[46],"non-IIDness.":[48],"However,":[49],"they":[50],"only":[51],"focus":[52],"provided":[57],"that":[58],"universal":[60,70],"class":[61,71],"distribution":[62,72],"balanced.":[64],"In":[65],"many":[66],"real-world":[67],"applications,":[68],"long-tailed,":[74],"which":[75],"causes":[76],"model":[78,116],"seriously":[79],"biased.":[80],"Therefore,":[81],"this":[82],"paper":[83],"studies":[84],"joint":[86],"problem":[87,148],"and":[90,96,138,156,173],"long-tailed":[91],"in":[93,164],"proposes":[97],"corresponding":[99],"solution":[100],"called":[101],"Ensemble":[103],"Distillation":[104],"Imbalance":[106],"Calibration":[107],"(FEDIC).":[108],"To":[109],"deal":[110],"data,":[113],"FEDIC":[114,152],"uses":[115],"ensemble":[117],"take":[119],"advantage":[120],"diversity":[123],"trained":[126],"Then,":[130],"new":[132],"distillation":[133],"method":[134],"logit":[136],"adjustment":[137],"calibration":[139],"gating":[140],"network":[141],"solve":[145],"long-tail":[147,174],"effectively.":[149],"We":[150],"evaluate":[151],"CIFAR-10-LT,":[154],"CIFAR-100-LT,":[155],"ImageNet-LT":[157],"highly":[160],"experimental":[162],"setting,":[163],"comparison":[165],"state-of-the-art":[168],"Our":[176],"code":[177],"available":[179],"at":[180],"https://github.com/shangxinyi/FEDIC.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}