{"id":"https://openalex.org/W4402981409","doi":"https://doi.org/10.1109/icme57554.2024.10687461","title":"Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statistics","display_name":"Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statistics","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981409","doi":"https://doi.org/10.1109/icme57554.2024.10687461"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5111346996","display_name":"Zhuoxin Chen","orcid":null},"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":"Zhuoxin Chen","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/A5100773431","display_name":"Zhenyu Wu","orcid":"https://orcid.org/0000-0003-0981-5567"},"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":"Zhenyu Wu","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/A5028862897","display_name":"Yang Ji","orcid":"https://orcid.org/0000-0002-4315-761X"},"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":"Yang Ji","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":null,"has_fulltext":false,"cited_by_count":4,"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":0.9975000023841858,"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":0.9975000023841858,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9506999850273132,"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/T10057","display_name":"Face and Expression Recognition","score":0.9309999942779541,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6633529663085938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5910835266113281},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5252753496170044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3972175419330597},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3210800886154175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17804384231567383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633529663085938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5910835266113281},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5252753496170044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3972175419330597},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3210800886154175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17804384231567383},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2440599146","https://openalex.org/W2963351448","https://openalex.org/W2995022099","https://openalex.org/W3034601242","https://openalex.org/W3176639943","https://openalex.org/W3182158470","https://openalex.org/W3202223295","https://openalex.org/W3203770998","https://openalex.org/W4285603347","https://openalex.org/W4366352743"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Federated":[0,75],"learning":[1,76,111],"is":[2],"designed":[3],"to":[4,46,58,100,105,135,140,145],"enhance":[5,109,141],"data":[6,17,147],"security":[7],"and":[8,20,62,108,129,132,154,173],"privacy,":[9],"but":[10],"faces":[11],"challenges":[12],"when":[13],"dealing":[14],"with":[15,43,157],"heterogeneous":[16],"in":[18,170],"long-tailed":[19,146,159],"non-IID":[21],"distributions.":[22,148],"This":[23],"paper":[24],"explores":[25],"an":[26],"overlooked":[27],"scenario":[28],"where":[29],"tail":[30],"classes":[31,45],"are":[32],"sparsely":[33],"distributed":[34],"over":[35],"a":[36,48,72],"few":[37],"clients,":[38],"causing":[39],"the":[40,83,86,89,116,137,142],"models":[41,102],"trained":[42],"these":[44],"have":[47],"lower":[49],"probability":[50],"of":[51],"being":[52],"selected":[53],"during":[54],"client":[55],"aggregation,":[56],"leading":[57],"slower":[59],"convergence":[60,107,174],"rates":[61],"poorer":[63],"model":[64],"performance.":[65],"To":[66],"address":[67],"this":[68],"issue,":[69],"we":[70],"propose":[71],"two-stage":[73],"Decoupled":[74],"framework":[77],"using":[78],"Feature":[79],"Statistics":[80],"(DFL-FS).":[81],"In":[82,115],"first":[84],"stage,":[85,118],"server":[87],"estimates":[88],"client\u2019s":[90],"class":[91],"coverage":[92],"distributions":[93],"through":[94],"masked":[95],"local":[96],"feature":[97,110,122,127],"statistics":[98,128],"clustering":[99],"select":[101],"for":[103],"aggregation":[104],"accelerate":[106],"without":[112],"privacy":[113],"leakage.":[114],"second":[117],"DFL-FS":[119],"employs":[120],"federated":[121],"regeneration":[123],"based":[124],"on":[125,152],"global":[126,138],"utilizes":[130],"resampling":[131],"weighted":[133],"covariance":[134],"calibrate":[136],"classifier":[139],"model's":[143],"adaptability":[144],"We":[149],"conducted":[150],"experiments":[151],"CIFAR10-LT":[153],"CIFAR100-LT":[155],"datasets":[156],"various":[158],"rates.":[160],"The":[161],"results":[162],"demonstrate":[163],"that":[164],"our":[165],"method":[166],"outperforms":[167],"state-of-the-art":[168],"methods":[169],"both":[171],"accuracy":[172],"rate.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}