{"id":"https://openalex.org/W4290875695","doi":"https://doi.org/10.1145/3534678.3539328","title":"Communication-Efficient Robust Federated Learning with Noisy Labels","display_name":"Communication-Efficient Robust Federated Learning with Noisy Labels","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290875695","doi":"https://doi.org/10.1145/3534678.3539328"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539328","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.05558","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100363213","display_name":"Junyi Li","orcid":"https://orcid.org/0000-0003-1543-3311"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junyi Li","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian Pei","raw_affiliation_strings":["Simon Fraser University, Greater Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Greater Vancouver, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060016795","display_name":"Heng Huang","orcid":"https://orcid.org/0000-0002-3483-8333"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Huang","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100363213"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":1.986,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8857264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"914","last_page":"924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9902999997138977,"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":0.9761999845504761,"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":0.8573879599571228},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6774469017982483},{"id":"https://openalex.org/keywords/bilevel-optimization","display_name":"Bilevel optimization","score":0.6380361318588257},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5840440988540649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5661979913711548},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5586705207824707},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5516289472579956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5357443690299988},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5256838798522949},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5217182040214539},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.47776663303375244},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.4590604901313782},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21046122908592224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8573879599571228},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6774469017982483},{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.6380361318588257},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5840440988540649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5661979913711548},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5586705207824707},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5516289472579956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5357443690299988},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5256838798522949},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5217182040214539},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47776663303375244},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.4590604901313782},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21046122908592224},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539328","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.05558","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.05558","pdf_url":"https://arxiv.org/pdf/2206.05558","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.05558","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.05558","pdf_url":"https://arxiv.org/pdf/2206.05558","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4824690120","display_name":null,"funder_award_id":"1845666, 1852606, 1838627, 1837956, 1956002, 2040588","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1866935739","https://openalex.org/W1868018859","https://openalex.org/W2004895663","https://openalex.org/W2064379477","https://openalex.org/W2080745194","https://openalex.org/W2112796928","https://openalex.org/W2157988812","https://openalex.org/W2187061624","https://openalex.org/W2270245739","https://openalex.org/W2541884796","https://openalex.org/W2606904667","https://openalex.org/W2617766261","https://openalex.org/W2774000609","https://openalex.org/W2786022758","https://openalex.org/W2787415863","https://openalex.org/W2791397041","https://openalex.org/W2904760378","https://openalex.org/W2911863041","https://openalex.org/W2912592113","https://openalex.org/W2914752403","https://openalex.org/W2947380870","https://openalex.org/W2950826569","https://openalex.org/W2951104886","https://openalex.org/W2963318081","https://openalex.org/W2963752132","https://openalex.org/W2963819344","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2967497108","https://openalex.org/W2981206218","https://openalex.org/W2982654255","https://openalex.org/W2988803701","https://openalex.org/W2996442797","https://openalex.org/W3001825675","https://openalex.org/W3003380256","https://openalex.org/W3004409745","https://openalex.org/W3037674050","https://openalex.org/W3039383564","https://openalex.org/W3043574444","https://openalex.org/W3081918527","https://openalex.org/W3088668959","https://openalex.org/W3092809425","https://openalex.org/W3108055363","https://openalex.org/W3114555490","https://openalex.org/W3118608800","https://openalex.org/W3126652544","https://openalex.org/W3129362180","https://openalex.org/W3159623990","https://openalex.org/W3162173877","https://openalex.org/W3175103763","https://openalex.org/W3175548922","https://openalex.org/W3184123939","https://openalex.org/W3213825583","https://openalex.org/W4224929776","https://openalex.org/W4225852813","https://openalex.org/W4229016916","https://openalex.org/W4244364296","https://openalex.org/W4249843299","https://openalex.org/W4287115303","https://openalex.org/W4287286018","https://openalex.org/W4287720355","https://openalex.org/W4287750664","https://openalex.org/W4288110990","https://openalex.org/W4288417148","https://openalex.org/W4289147229","https://openalex.org/W4295292688","https://openalex.org/W4308902126","https://openalex.org/W4318619660","https://openalex.org/W4394651377","https://openalex.org/W6686960354","https://openalex.org/W6758757267","https://openalex.org/W6759172331"],"related_works":["https://openalex.org/W2890257643","https://openalex.org/W1495503294","https://openalex.org/W2161149697","https://openalex.org/W3090200643","https://openalex.org/W2340378315","https://openalex.org/W255338418","https://openalex.org/W2013038594","https://openalex.org/W1604175135","https://openalex.org/W2602322400","https://openalex.org/W3149055374"],"abstract_inverted_index":{"Federated":[0,126,165,191],"learning":[1,8,55],"(FL)":[2],"is":[3,18,50,133,168,180,212],"a":[4,81,98,114,125,134],"promising":[5],"privacy-preserving":[6],"machine":[7],"paradigm":[9],"over":[10,113],"distributed":[11],"located":[12],"data.":[13],"In":[14,71],"FL,":[15],"the":[16,26,32,41,53,66,87,106,119,164,173,181,189,204,209,218,223],"data":[17,37,42],"kept":[19],"locally":[20],"by":[21],"each":[22,101],"user.":[23],"This":[24],"protects":[25],"user":[27],"privacy,":[28],"but":[29],"also":[30,213],"makes":[31],"server":[33],"difficult":[34],"to":[35,52,63,85,187,202,221,238],"verify":[36],"quality,":[38],"especially":[39],"if":[40],"are":[43],"correctly":[44],"labeled.":[45],"Training":[46],"with":[47,139,154],"corrupted":[48],"labels":[49,91],"harmful":[51],"federated":[54],"task;":[56],"however,":[57],"little":[58],"attention":[59],"has":[60,109,229],"been":[61],"paid":[62],"FL":[64],"in":[65,92,177],"case":[67],"of":[68,89,136,142,208],"label":[69,225],"noise.":[70],"this":[72,77],"paper,":[73],"we":[74,96,185,197,216],"focus":[75],"on":[76,233],"problem":[78,132,138],"and":[79],"propose":[80,198],"learning-based":[82],"reweighting":[83],"approach":[84,228],"mitigate":[86],"effect":[88],"noisy":[90,224],"FL.":[93],"More":[94,117],"precisely,":[95],"tuned":[97],"weight":[99],"for":[100],"training":[102],"sample":[103],"such":[104],"that":[105,172],"learned":[107],"model":[108],"optimal":[110],"generalization":[111],"performance":[112,232],"validation":[115],"set.":[116],"formally,":[118],"process":[120],"can":[121],"be":[122],"formulated":[123],"as":[124],"Bilevel":[127,130,192],"Optimization":[128,193],"problem.":[129,226],"optimization":[131,137,161],"type":[135],"two":[140,199],"levels":[141],"entangled":[143],"problems.":[144],"The":[145],"non-distributed":[146],"bilevel":[147,160],"problems":[148,162],"have":[149],"witnessed":[150],"notable":[151],"progress":[152],"recently":[153],"new":[155],"efficient":[156],"algorithms.":[157],"However,":[158],"solving":[159],"under":[163],"Learning":[166],"setting":[167],"under-investigated.":[169],"We":[170],"identify":[171],"high":[174],"communication":[175],"cost":[176],"hypergradient":[178],"evaluation":[179],"major":[182],"bottleneck.":[183],"So":[184],"proposeComm-FedBiO":[186],"solve":[188,222],"general":[190],"problems;":[194],"more":[195],"specifically,":[196],"communication-efficient":[200],"subroutines":[201],"estimate":[203],"hypergradient.":[205],"Convergence":[206],"analysis":[207],"proposed":[210,219],"algorithms":[211,220],"provided.":[214],"Finally,":[215],"apply":[217],"Our":[227],"shown":[230],"superior":[231],"several":[234],"real-world":[235],"datasets":[236],"compared":[237],"various":[239],"baselines.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}