{"id":"https://openalex.org/W3103354558","doi":null,"title":"Federated Multi-Mini-Batch: An Efficient Training Approach to Federated Learning in Non-IID Environments.","display_name":"Federated Multi-Mini-Batch: An Efficient Training Approach to Federated Learning in Non-IID Environments.","publication_year":2020,"publication_date":"2020-11-13","ids":{"openalex":"https://openalex.org/W3103354558","mag":"3103354558"},"language":"en","primary_location":{"id":"mag:3103354558","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.07006","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2011.07006","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080057671","display_name":"Mohammad Bakhtiari","orcid":"https://orcid.org/0000-0002-4169-9669","observed_orcids":["https://orcid.org/0000-0002-4169-9669"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Bakhtiari","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4169-9669","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048531338","display_name":"Reza Nasirigerdeh","orcid":"https://orcid.org/0000-0002-2283-5792","observed_orcids":["https://orcid.org/0000-0002-2283-5792"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reza Nasirigerdeh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2283-5792","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005090755","display_name":"Reihaneh Torkzadehmahani","orcid":"https://orcid.org/0000-0003-0851-2185","observed_orcids":["https://orcid.org/0000-0003-0851-2185"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reihaneh Torkzadehmahani","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0851-2185","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000776955","display_name":"Amirhossein Bayat","orcid":"https://orcid.org/0000-0003-1129-9725","observed_orcids":["https://orcid.org/0000-0003-1129-9725"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amirhossein Bayat","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1129-9725","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087738237","display_name":"David B. Blumenthal","orcid":"https://orcid.org/0000-0001-8651-750X","observed_orcids":["https://orcid.org/0000-0001-8651-750X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David B. Blumenthal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035928806","display_name":"Markus List","orcid":"https://orcid.org/0000-0002-0941-4168","observed_orcids":["https://orcid.org/0000-0002-0941-4168"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus List","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0941-4168","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073222532","display_name":"Jan Baumbach","orcid":"https://orcid.org/0000-0002-0282-0462","observed_orcids":["https://orcid.org/0000-0002-0282-0462"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Baumbach","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0282-0462","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/federated-learning","display_name":"federated learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.9679999947547913},{"id":"https://openalex.org/keywords/fedavg","display_name":"FedAvg","score":0.7760000228881836},{"id":"https://openalex.org/keywords/communication-efficiency","display_name":"communication efficiency","score":0.9549999833106995},{"id":"https://openalex.org/keywords/batch-size","display_name":"batch size","score":0.6200000047683716},{"id":"https://openalex.org/keywords/privacy-preserving-training","display_name":"privacy-preserving training","score":0.7070000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120403289794922},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7294053435325623},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.6957730054855347},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6278533935546875},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5633638501167297},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.5126110911369324},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4886517822742462},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3301343321800232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3077363967895508},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.20194274187088013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08445900678634644},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06504586338996887},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3103354558","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.07006","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3103354558","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.07006","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1532854728","https://openalex.org/W1686810756","https://openalex.org/W1955857676","https://openalex.org/W2116612304","https://openalex.org/W2402144811","https://openalex.org/W2523246573","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2750384547","https://openalex.org/W2783522756","https://openalex.org/W2807006176","https://openalex.org/W2897230576","https://openalex.org/W2900120080","https://openalex.org/W2903471046","https://openalex.org/W2904190483","https://openalex.org/W2914328083","https://openalex.org/W2918777711","https://openalex.org/W2978110818","https://openalex.org/W2995022099","https://openalex.org/W2995653155","https://openalex.org/W2996736801","https://openalex.org/W3018464563","https://openalex.org/W3019609389","https://openalex.org/W3047304572","https://openalex.org/W3102785203","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W4200079028","https://openalex.org/W7221770962","https://openalex.org/W3035927627","https://openalex.org/W4286229207","https://openalex.org/W3196405711","https://openalex.org/W4411584266","https://openalex.org/W4283771741","https://openalex.org/W3204468048","https://openalex.org/W4323521275","https://openalex.org/W3184838508"],"abstract_inverted_index":{"Federated":[0,17],"learning":[1,220],"is":[2,20,38,174,213],"a":[3,10,21,47,53,61,88,113,129,162,181],"well-established":[4],"approach":[5,217],"to":[6,59,67,218],"privacy-preserving":[7],"training":[8,107,216],"of":[9,56,104,116,131,202],"joint":[11],"model":[12,86,138],"on":[13,87,139],"heavily":[14],"distributed":[15,42],"data.":[16],"averaging":[18],"(FedAvg)":[19],"well-known":[22],"communication-efficient":[23],"algorithm":[24],"for":[25],"federated":[26,77,125,219],"learning,":[27],"which":[28,180],"performs":[29],"well":[30,208],"if":[31],"the":[32,36,72,82,85,102,105,120,134,137,144,153,157,165,186,203],"data":[33],"distribution":[34],"across":[35],"clients":[37,83,135],"independently":[39],"and":[40,50,160,167,189,212],"identically":[41],"(IID).":[43],"However,":[44],"FedAvg":[45,199],"provides":[46,161],"lower":[48],"accuracy":[49,63,103,166],"still":[51],"requires":[52],"large":[54],"number":[55,115],"communication":[57,149,168,205],"rounds":[58],"achieve":[60],"target":[62],"when":[64],"it":[65],"comes":[66],"Non-IID":[68,109,171,222],"environments.":[69,223],"To":[70,118],"address":[71,119],"former":[73],"limitation,":[74,122],"we":[75,123],"present":[76],"single":[78,89,182],"mini-batch":[79,90],"(FedSMB),":[80],"where":[81,133],"train":[84,136],"from":[91,156],"their":[92],"dataset":[93],"in":[94,108,112,147,170,179,200,221],"each":[95,148],"iteration.":[96],"We":[97],"show":[98],"that":[99,196],"FedSMB":[100],"achieves":[101],"centralized":[106],"configurations,":[110],"but":[111],"considerable":[114],"iterations.":[117],"latter":[121],"introduce":[124],"multi-mini-batch":[126],"(FedMMB)":[127],"as":[128,207,209],"generalization":[130],"FedSMB,":[132],"multiple":[140],"mini-batches":[141],"(specified":[142],"by":[143],"batch":[145,154,158,187,190],"count)":[146],"round.":[150],"FedMMB":[151,197],"decouples":[152],"size":[155,188],"count":[159],"trade-off":[163],"between":[164],"efficiency":[169,211],"settings.":[172],"This":[173],"not":[175],"possible":[176],"with":[177],"FedAvg,":[178],"parameter":[183],"determines":[184],"both":[185],"count.":[191],"The":[192],"simulation":[193],"results":[194],"illustrate":[195],"outperforms":[198],"terms":[201],"accuracy,":[204],"efficiency,":[206],"computational":[210],"an":[214],"efficient":[215]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2020-11-23T00:00:00"}