{"id":"https://openalex.org/W4404037594","doi":"https://doi.org/10.1109/allerton63246.2024.10735294","title":"Communication-Efficient Federated Learning via Sparse Training with Regularized Error Correction","display_name":"Communication-Efficient Federated Learning via Sparse Training with Regularized Error Correction","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4404037594","doi":"https://doi.org/10.1109/allerton63246.2024.10735294"},"language":"en","primary_location":{"id":"doi:10.1109/allerton63246.2024.10735294","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton63246.2024.10735294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 60th Annual Allerton Conference on Communication, Control, and Computing","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/A5093567674","display_name":"Ran Greidi","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ran Greidi","raw_affiliation_strings":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev,Beer-Sheva,Israel,84105"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev,Beer-Sheva,Israel,84105","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066085947","display_name":"Kobi Cohen","orcid":"https://orcid.org/0000-0003-0532-009X"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Kobi Cohen","raw_affiliation_strings":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev,Beer-Sheva,Israel,84105"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev,Beer-Sheva,Israel,84105","institution_ids":["https://openalex.org/I124227911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66253448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.972000002861023,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9713000059127808,"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":0.7950817346572876},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6673039197921753},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5823743939399719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46309900283813477},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4360004663467407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3843279778957367},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1922703981399536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950817346572876},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6673039197921753},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5823743939399719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46309900283813477},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4360004663467407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3843279778957367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1922703981399536},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/allerton63246.2024.10735294","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton63246.2024.10735294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 60th Annual Allerton Conference on Communication, Control, and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5755329095","display_name":null,"funder_award_id":"2640/20","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2405578611","https://openalex.org/W2606891064","https://openalex.org/W2774000609","https://openalex.org/W2805997383","https://openalex.org/W2898754723","https://openalex.org/W2962965870","https://openalex.org/W2969343398","https://openalex.org/W2978015420","https://openalex.org/W2989289980","https://openalex.org/W2999204576","https://openalex.org/W3015613093","https://openalex.org/W3015640161","https://openalex.org/W3045590453","https://openalex.org/W3046653923","https://openalex.org/W3088234149","https://openalex.org/W3090615085","https://openalex.org/W3101036738","https://openalex.org/W3108590825","https://openalex.org/W3121362365","https://openalex.org/W3148526481","https://openalex.org/W3192007187","https://openalex.org/W3202820162","https://openalex.org/W3202869544","https://openalex.org/W4212774754","https://openalex.org/W4283320273","https://openalex.org/W4285302300","https://openalex.org/W4287720355","https://openalex.org/W4313155634","https://openalex.org/W4313627870","https://openalex.org/W4318619660","https://openalex.org/W4330337811","https://openalex.org/W4377090735","https://openalex.org/W4379781012","https://openalex.org/W4382752549","https://openalex.org/W4386902918","https://openalex.org/W4391019723","https://openalex.org/W4402592942","https://openalex.org/W6677580257","https://openalex.org/W6726275242","https://openalex.org/W6728757088","https://openalex.org/W6746839373","https://openalex.org/W6751248777","https://openalex.org/W6752012617","https://openalex.org/W6755251367","https://openalex.org/W6780897730","https://openalex.org/W6809704105","https://openalex.org/W6839799260","https://openalex.org/W6850543012","https://openalex.org/W6853393724"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Federated":[0,134],"Learning":[1,135],"(FL)":[2],"is":[3,75,204],"an":[4,180],"emerging":[5],"paradigm":[6],"that":[7,187],"allows":[8],"for":[9],"decentralized":[10],"machine":[11],"learning":[12],"(ML),":[13],"where":[14,79],"multiple":[15],"models":[16,34,158],"are":[17,30,83,93],"collaboratively":[18],"trained":[19],"in":[20,35,47,56,164,195],"a":[21,76,104,130,147,169,214],"privacy-preserving":[22],"manner.":[23],"However,":[24],"since":[25],"communications":[26],"and":[27,44,90,176,210,220],"computation":[28],"resources":[29],"limited,":[31],"training":[32,51,150],"DNN":[33],"FL":[36,166],"systems":[37],"face":[38],"challenges":[39],"such":[40],"as":[41],"elevated":[42],"computational":[43],"communication":[45],"costs":[46],"complex":[48,211],"tasks.":[49],"Sparse":[50],"schemes":[52],"gain":[53],"increasing":[54],"attention":[55],"order":[57],"to":[58,85,102,121,141,172,179],"scale":[59],"down":[60],"the":[61,86,91,109,122,156,162,165,173,223],"dimensionality":[62],"of":[63,108,155,202],"each":[64],"client":[65],"(i.e.,":[66],"node)":[67],"transmission.":[68],"Specifically,":[69],"sparsification":[70,106],"with":[71,136,159,197,227],"error":[72,97,190],"correction":[73,98],"methods":[74,99],"promising":[77],"technique,":[78],"only":[80],"important":[81],"updates":[82],"sent":[84],"parameter":[87],"server":[88],"(PS)":[89],"rest":[92],"accumulated":[94,153],"locally.":[95],"While":[96],"have":[100],"shown":[101],"achieve":[103],"significant":[105,193],"level":[107,217],"client-to-PS":[110],"message":[111],"without":[112],"harming":[113],"convergence,":[114],"pushing":[115,177],"sparsity":[116,178,198,216],"further":[117],"remains":[118],"unresolved":[119],"due":[120],"staleness":[123,174],"effect.":[124],"In":[125],"this":[126,143],"paper,":[127],"we":[128],"propose":[129],"novel":[131,148],"algorithm,":[132],"dubbed":[133],"Accumulated":[137],"Regularized":[138],"Embeddings":[139],"(FLARE),":[140],"overcome":[142],"challenge.":[144],"FLARE":[145,203],"presents":[146],"sparse":[149],"approach":[151],"via":[152],"pulling":[154],"updated":[157],"regularization":[160],"on":[161,208],"embeddings":[163],"process,":[167],"providing":[168],"powerful":[170],"solution":[171],"effect,":[175],"exceptional":[181],"level.":[182],"Our":[183],"theoretical":[184],"analysis":[185],"demonstrates":[186],"FLARE's":[188],"regularized":[189],"feedback":[191],"achieves":[192],"improvements":[194],"scalability":[196],"parameter.":[199],"The":[200],"performance":[201],"validated":[205],"through":[206],"experiments":[207],"diverse":[209],"models,":[212],"achieving":[213],"remarkable":[215],"(10":[218],"times":[219],"more":[221],"beyond":[222],"current":[224],"state-of-the-art)":[225],"along":[226],"significantly":[228],"improved":[229],"accuracy.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}