{"id":"https://openalex.org/W4392699570","doi":"https://doi.org/10.1145/3615593.3615720","title":"FedCOM","display_name":"FedCOM","publication_year":2023,"publication_date":"2023-10-06","ids":{"openalex":"https://openalex.org/W4392699570","doi":"https://doi.org/10.1145/3615593.3615720"},"language":"en","primary_location":{"id":"doi:10.1145/3615593.3615720","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615593.3615720","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615593.3615720","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3615593.3615720","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101670597","display_name":"Xintong Lu","orcid":"https://orcid.org/0009-0007-0531-9802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xintong Lu","raw_affiliation_strings":["BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0531-9802","affiliations":[{"raw_affiliation_string":"BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649609","display_name":"Yuchao Zhang","orcid":"https://orcid.org/0000-0002-0135-8915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchao Zhang","raw_affiliation_strings":["BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0135-8915","affiliations":[{"raw_affiliation_string":"BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015576911","display_name":"Huan Zou","orcid":"https://orcid.org/0000-0002-7409-3700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Zou","raw_affiliation_strings":["BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7409-3700","affiliations":[{"raw_affiliation_string":"BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066484218","display_name":"Yilei Liang","orcid":"https://orcid.org/0000-0002-0520-8105"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yilei Liang","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"raw_orcid":"https://orcid.org/0000-0002-0520-8105","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329067","display_name":"Wendong Wang","orcid":"https://orcid.org/0000-0002-6418-8087"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wendong Wang","raw_affiliation_strings":["BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6418-8087","affiliations":[{"raw_affiliation_string":"BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062093738","display_name":"Jon Crowcroft","orcid":"https://orcid.org/0000-0002-7013-0121"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Crowcroft","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"raw_orcid":"https://orcid.org/0000-0002-7013-0121","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2428,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62114851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9958000183105469,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9897000193595886,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9502999782562256,"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":0.4966357350349426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4966357350349426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3615593.3615720","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615593.3615720","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615593.3615720","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3615593.3615720","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615593.3615720","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615593.3615720","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392699570.pdf","grobid_xml":"https://content.openalex.org/works/W4392699570.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W2112796928","https://openalex.org/W2295107390","https://openalex.org/W2962858109","https://openalex.org/W2963446712","https://openalex.org/W3034163621","https://openalex.org/W3042621011","https://openalex.org/W3092408317","https://openalex.org/W3133814152","https://openalex.org/W4285876308","https://openalex.org/W4286421857"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Personalized":[0,114],"federated":[1,10,188],"learning":[2],"aims":[3],"to":[4,23,50,67,100,127,135,179],"address":[5],"two":[6,107],"key":[7,108],"challenges":[8],"in":[9,147],"systems:":[11],"performance":[12],"degradation":[13],"of":[14,21,27,106,120,173],"the":[15,19,121,148,181,186],"global":[16,46],"model,":[17],"and":[18,43,76,113,167,176,185],"lack":[20],"specificity":[22],"individual":[24],"clients.":[25,80],"Both":[26],"them":[28],"are":[29],"caused":[30],"by":[31],"client":[32,95],"heterogeneity.":[33],"Previous":[34],"solutions":[35],"often":[36],"assume":[37],"all":[38],"clients":[39],"have":[40],"similar":[41,48],"tasks,":[42],"always":[44],"utilize":[45],"or":[47],"models":[49,54,141],"gain":[51],"better":[52],"personalized":[53,187],"for":[55,123],"each":[56,94],"client.":[57],"However,":[58],"we":[59,85,139],"found":[60],"they":[61],"can't":[62],"work":[63],"well":[64],"when":[65],"came":[66],"a":[68],"common":[69],"task-heterogenic":[70],"scenario,":[71],"with":[72,169],"skewed":[73],"label":[74],"distribution":[75],"complementary":[77,143],"relationships":[78],"between":[79],"To":[81],"tackle":[82],"this":[83],"issue,":[84],"propose":[86],"FedCOM,":[87],"an":[88,170],"innovative":[89],"workflow":[90],"that":[91,131,154],"can":[92,156],"help":[93],"find":[96],"its":[97],"best":[98],"peers":[99,144],"learn":[101],"from.":[102],"Our":[103],"method":[104,189],"consists":[105],"components:":[109],"Complementary":[110],"Client":[111],"Matching":[112],"Federated":[115],"Learning.":[116],"We":[117],"take":[118],"gradients":[119],"loss":[122],"target":[124],"minority":[125],"classes":[126],"identify":[128],"feature":[129],"channels":[130],"make":[132],"significant":[133],"contributions":[134],"classification":[136],"scores.":[137],"Subsequently,":[138],"introduce":[140],"from":[142],"as":[145],"regularizers":[146],"local":[149],"personalization":[150],"objectives.":[151],"Experiments":[152],"demonstrate":[153],"FedCOM":[155],"achieve":[157],"faster":[158],"convergence,":[159],"while":[160],"maintaining":[161],"higher":[162],"accuracy":[163],"on":[164],"MNIST,":[165],"Fashion-MNIST,":[166],"CIFAR-10":[168],"average":[171],"improvement":[172],"41.78%,":[174],"23.74%,":[175],"1.25%":[177],"compared":[178],"FedProx,":[180],"clustering":[182],"algorithm":[183],"IFCA":[184],"Ditto.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-03-13T00:00:00"}