{"id":"https://openalex.org/W3160164683","doi":"https://doi.org/10.1109/icassp39728.2021.9413927","title":"Demystifying Model Averaging for Communication-Efficient Federated Matrix Factorization","display_name":"Demystifying Model Averaging for Communication-Efficient Federated Matrix Factorization","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160164683","doi":"https://doi.org/10.1109/icassp39728.2021.9413927","mag":"3160164683"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["School of Science & Engineering, The Chinese University of Hong Kong, Shenzhen, China","Shenzhen Research Institute of Big Data, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science & Engineering, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050143971","display_name":"Richard Cornelius Suwandi","orcid":"https://orcid.org/0009-0001-7894-1674"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richard Cornelius Suwandi","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064271996","display_name":"Tsung\u2010Hui Chang","orcid":"https://orcid.org/0000-0003-1349-2764"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tsung-Hui Chang","raw_affiliation_strings":["School of Science & Engineering, The Chinese University of Hong Kong, Shenzhen, China","Shenzhen Research Institute of Big Data, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science & Engineering, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3680","last_page":"3684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9918000102043152,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9918000102043152,"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":0.9887999892234802,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8356846570968628},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7011930346488953},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6153781414031982},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6001972556114197},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5564506649971008},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5530135631561279},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5062243342399597},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4688716232776642},{"id":"https://openalex.org/keywords/models-of-communication","display_name":"Models of communication","score":0.4222140312194824},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4147527813911438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40574511885643005},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37960320711135864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3749259114265442},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3600483536720276},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3247894048690796},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29604536294937134},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.08682933449745178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356846570968628},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7011930346488953},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6153781414031982},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6001972556114197},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5564506649971008},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5530135631561279},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5062243342399597},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4688716232776642},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.4222140312194824},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4147527813911438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40574511885643005},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37960320711135864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3749259114265442},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3600483536720276},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3247894048690796},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29604536294937134},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.08682933449745178},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/icassp39728.2021.9413927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":46,"referenced_works":["https://openalex.org/W123735952","https://openalex.org/W182774073","https://openalex.org/W1980147176","https://openalex.org/W2025183726","https://openalex.org/W2029463952","https://openalex.org/W2054141820","https://openalex.org/W2073459066","https://openalex.org/W2108399535","https://openalex.org/W2116612304","https://openalex.org/W2132692097","https://openalex.org/W2136635436","https://openalex.org/W2144335278","https://openalex.org/W2153622543","https://openalex.org/W2164616133","https://openalex.org/W2407044469","https://openalex.org/W2530417694","https://openalex.org/W2541884796","https://openalex.org/W2617960902","https://openalex.org/W2777333837","https://openalex.org/W2804903923","https://openalex.org/W2900182564","https://openalex.org/W2912592113","https://openalex.org/W2939782843","https://openalex.org/W2947861550","https://openalex.org/W2955213239","https://openalex.org/W2962688627","https://openalex.org/W2963228337","https://openalex.org/W2963889845","https://openalex.org/W2963900715","https://openalex.org/W2995653155","https://openalex.org/W3013686349","https://openalex.org/W3038022836","https://openalex.org/W3047789363","https://openalex.org/W4206519735","https://openalex.org/W4318619660","https://openalex.org/W6607482675","https://openalex.org/W6668990524","https://openalex.org/W6681503828","https://openalex.org/W6728757088","https://openalex.org/W6738250615","https://openalex.org/W6751858026","https://openalex.org/W6752750811","https://openalex.org/W6758757267","https://openalex.org/W6759238902","https://openalex.org/W6762754822","https://openalex.org/W6765541894"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840"],"abstract_inverted_index":{"Federated":[0],"learning":[1,88],"(FL)":[2],"is":[3,32],"encountered":[4],"with":[5,136,149],"the":[6,45,60,75,95,111,124,137,142],"challenge":[7],"of":[8,39,126,169],"training":[9],"a":[10,22,35,49,65,101],"model":[11],"in":[12,58,146,167],"massive":[13],"and":[14,86,99,115,129,160,173],"heterogeneous":[15,147],"networks.":[16],"Model":[17],"averaging":[18],"(MA)":[19],"has":[20,54,70,82],"become":[21],"popular":[23],"FL":[24],"paradigm":[25],"where":[26],"parallel":[27],"(stochastic)":[28],"gradient":[29],"descent":[30],"(GD)":[31],"run":[33],"on":[34],"small":[36],"sampled":[37],"subset":[38],"clients":[40,133],"multiple":[41],"times":[42],"before":[43],"uploading":[44],"local":[46,127],"models":[47],"to":[48,134,157],"server":[50,138],"for":[51,63,74],"averaging,":[52],"which":[53,81],"been":[55,72],"proven":[56],"effective":[57],"reducing":[59],"communication":[61,143,174],"cost":[62],"achieving":[64],"good":[66],"model.":[67],"However,":[68],"MA":[69,103],"not":[71],"considered":[73],"important":[76],"matrix":[77],"factorization":[78],"(MF)":[79],"model,":[80],"vast":[83],"signal":[84],"processing":[85],"machine":[87],"applications.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93,119],"investigate":[94],"federated":[96],"MF":[97],"problem":[98],"propose":[100],"new":[102],"based":[104],"algorithm,":[105],"named":[106],"FedMAvg,":[107],"by":[108,154],"judiciously":[109],"combining":[110],"alternating":[112],"minimization":[113],"technique":[114],"MA.":[116],"Through":[117],"analysis,":[118],"show":[120],"that":[121],"gradually":[122],"decreasing":[123],"number":[125],"GD":[128],"only":[130],"allowing":[131],"partial":[132],"communicate":[135],"can":[139],"greatly":[140],"reduce":[141],"cost,":[144],"especially":[145],"networks":[148],"non-i.i.d.":[150],"data.":[151],"Experimental":[152],"results":[153],"applying":[155],"FedMAvg":[156],"data":[158],"clustering":[159],"item":[161],"recommendation":[162],"tasks":[163],"demonstrate":[164],"its":[165],"efficacy":[166],"terms":[168],"both":[170],"task":[171],"performance":[172],"efficiency.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}