{"id":"https://openalex.org/W4312759323","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892777","title":"Optimized and Adaptive Federated Learning for Straggler-Resilient Device Selection","display_name":"Optimized and Adaptive Federated Learning for Straggler-Resilient Device Selection","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312759323","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892777"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892777","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5034661675","display_name":"Sourasekhar Banerjee","orcid":"https://orcid.org/0000-0002-3451-2851"},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sourasekhar Banerjee","raw_affiliation_strings":["Umeå University,Dept. of Computing Science,Umeå,Sweden,SE-907 81"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Umeå University,Dept. of Computing Science,Umeå,Sweden,SE-907 81","institution_ids":["https://openalex.org/I90267481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028720787","display_name":"Xuan-Son Vu","orcid":"https://orcid.org/0000-0001-8820-2405"},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xuan-Son Vu","raw_affiliation_strings":["Umeå University,Dept. of Computing Science,Umeå,Sweden,SE-907 81"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Umeå University,Dept. of Computing Science,Umeå,Sweden,SE-907 81","institution_ids":["https://openalex.org/I90267481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044933320","display_name":"Monowar Bhuyan","orcid":"https://orcid.org/0000-0002-9842-7840"},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Monowar Bhuyan","raw_affiliation_strings":["Umeå University,Dept. of Computing Science,Umeå,Sweden,SE-907 81"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Umeå University,Dept. of Computing Science,Umeå,Sweden,SE-907 81","institution_ids":["https://openalex.org/I90267481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90267481"],"apc_list":null,"apc_paid":null,"fwci":0.9348,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7715876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"9"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9825999736785889,"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":0.8166278600692749},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8069430589675903},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7028526067733765},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4956420660018921},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4818117022514343},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4680478274822235},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46396079659461975},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4287397265434265},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40352484583854675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35599809885025024},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.27542006969451904},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22205054759979248},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1863524615764618},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1220981776714325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166278600692749},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8069430589675903},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7028526067733765},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4956420660018921},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4818117022514343},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4680478274822235},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46396079659461975},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4287397265434265},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40352484583854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35599809885025024},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27542006969451904},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22205054759979248},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1863524615764618},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1220981776714325},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892777","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2007339694","https://openalex.org/W2126105956","https://openalex.org/W2739512927","https://openalex.org/W2750384547","https://openalex.org/W2912592113","https://openalex.org/W2921434559","https://openalex.org/W2946193510","https://openalex.org/W2955213239","https://openalex.org/W2962863496","https://openalex.org/W2963179579","https://openalex.org/W2995022099","https://openalex.org/W3038022836","https://openalex.org/W3095593352","https://openalex.org/W3108109753","https://openalex.org/W3109504587","https://openalex.org/W3109723249","https://openalex.org/W3118608800","https://openalex.org/W3129682320","https://openalex.org/W3154608090","https://openalex.org/W3156313434","https://openalex.org/W3156953231","https://openalex.org/W3161598168","https://openalex.org/W3199079404","https://openalex.org/W3200187410","https://openalex.org/W3208300320","https://openalex.org/W3213859843","https://openalex.org/W4206139647","https://openalex.org/W4300427714","https://openalex.org/W4301183978","https://openalex.org/W4318619660","https://openalex.org/W6728757088","https://openalex.org/W6738383168","https://openalex.org/W6745458143","https://openalex.org/W6758757267","https://openalex.org/W6759238902","https://openalex.org/W6762879059","https://openalex.org/W6790589152","https://openalex.org/W6795136437","https://openalex.org/W6802667569","https://openalex.org/W6802956129"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W4389249638","https://openalex.org/W2733410219","https://openalex.org/W2734358244","https://openalex.org/W4388700941"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"has":[3,233],"evolved":[4],"as":[5],"a":[6,33,52,109],"promising":[7],"distributed":[8],"learning":[9,89],"paradigm":[10],"in":[11,21,87,121,149,174,243],"which":[12],"data":[13,43],"samples":[14],"are":[15,130],"disseminated":[16],"over":[17,78],"massively":[18],"connected":[19],"devices":[20,70,86,164,173,182,248],"an":[22],"IID":[23,254],"(Identical":[24],"and":[25,48,75,98,151,178,200,214,227,238,249,255],"Independent":[26],"Distribution)":[27],"or":[28,84],"non-IID":[29,216,256],"manner.":[30],"FL":[31,62,96,123],"follows":[32],"collaborative":[34],"training":[35,42,194],"approach":[36,114,170],"where":[37],"each":[38,141],"device":[39,210],"uses":[40],"local":[41,46,58,69],"to":[44,65,115,131,167,187],"train":[45],"models,":[47],"the":[49,57,88,93,117,122,134,137,144,147,153,157,184,189,204,228,244,250],"server":[50],"generates":[51],"global":[53,176],"model":[54,206,251],"by":[55],"combining":[56],"model's":[59,190,236],"parameters.":[60],"However,":[61],"is":[63,198,220],"vulnerable":[64],"system":[66],"heterogeneity":[67],"when":[68],"have":[71],"varying":[72],"computational,":[73],"storage,":[74],"communication":[76],"capabilities":[77],"time.":[79],"The":[80,125,160,169,192],"presence":[81],"of":[82,95,119,136,140,146,156,196,247],"stragglers":[83,120],"low-performing":[85],"process":[90],"severely":[91],"impacts":[92],"scalability":[94],"algorithms":[97],"significantly":[99,234],"delays":[100],"convergence.":[101],"To":[102],"mitigate":[103],"this":[104],"problem,":[105],"we":[106],"propose":[107],"Fed-MOODS,":[108],"Multi-Objective":[110],"Optimization-based":[111],"Device":[112],"Selection":[113],"reduce":[116],"effect":[118],"process.":[124],"primary":[126],"criteria":[127],"for":[128,212,252],"optimization":[129,162],"maximize:":[132],"(i)":[133],"availability":[135,145],"processing":[138],"capacity":[139,155],"device,":[142],"(ii)":[143],"memory":[148],"devices,":[150],"(iii)":[152],"bandwidth":[154],"participating":[158],"devices.":[159],"multi-objective":[161],"prioritizes":[163],"from":[165,183],"fast":[166],"slow.":[168],"involves":[171],"faster":[172,202],"early":[175],"rounds":[177],"gradually":[179],"incorporating":[180],"slower":[181],"Pareto":[185],"fronts":[186],"improve":[188],"accuracy.":[191],"overall":[193],"time":[195],"Fed-MOODS":[197,219,232,240],"1.8\u00d7":[199],"1.48\u00d7":[201],"than":[203],"baseline":[205],"(FedAvg)":[207],"with":[208],"random":[209],"selection":[211],"MNIST":[213],"FMNIST":[215],"data,":[217],"respectively.":[218],"extensively":[221],"evaluated":[222],"under":[223],"multiple":[224],"experimental":[225],"settings,":[226],"results":[229],"show":[230],"that":[231],"improved":[235],"convergence":[237],"performance.":[239],"maintains":[241],"fairness":[242],"prioritized":[245],"participation":[246],"both":[253],"settings.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}