{"id":"https://openalex.org/W3170790803","doi":"https://doi.org/10.1109/tccn.2021.3084406","title":"Fast-Convergent Federated Learning With Adaptive Weighting","display_name":"Fast-Convergent Federated Learning With Adaptive Weighting","publication_year":2021,"publication_date":"2021-05-27","ids":{"openalex":"https://openalex.org/W3170790803","doi":"https://doi.org/10.1109/tccn.2021.3084406","mag":"3170790803"},"language":"en","primary_location":{"id":"doi:10.1109/tccn.2021.3084406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tccn.2021.3084406","pdf_url":null,"source":{"id":"https://openalex.org/S2484188435","display_name":"IEEE Transactions on Cognitive Communications and Networking","issn_l":"2332-7731","issn":["2332-7731","2372-2045"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive Communications and Networking","raw_type":"journal-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/A5027167901","display_name":"Hongda Wu","orcid":"https://orcid.org/0000-0001-8244-928X"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hongda Wu","raw_affiliation_strings":["Lassonde School of Engineering, York University, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Lassonde School of Engineering, York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338634","display_name":"Ping Wang","orcid":"https://orcid.org/0000-0002-1599-5480"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ping Wang","raw_affiliation_strings":["Lassonde School of Engineering, York University, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Lassonde School of Engineering, York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027167901"],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":18.0547,"has_fulltext":false,"cited_by_count":199,"citation_normalized_percentile":{"value":0.99402044,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"7","issue":"4","first_page":"1078","last_page":"1088"},"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":0.9940999746322632,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6951523423194885},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.664093017578125},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5650864243507385},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5205212831497192},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.4939737915992737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4215850830078125},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32117530703544617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6951523423194885},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.664093017578125},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5650864243507385},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5205212831497192},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.4939737915992737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4215850830078125},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32117530703544617},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/tccn.2021.3084406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tccn.2021.3084406","pdf_url":null,"source":{"id":"https://openalex.org/S2484188435","display_name":"IEEE Transactions on Cognitive Communications and Networking","issn_l":"2332-7731","issn":["2332-7731","2372-2045"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive Communications and Networking","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1602393795","https://openalex.org/W1972284617","https://openalex.org/W2107152312","https://openalex.org/W2125826911","https://openalex.org/W2472333518","https://openalex.org/W2797816609","https://openalex.org/W2798720628","https://openalex.org/W2807006176","https://openalex.org/W2919115771","https://openalex.org/W2920095265","https://openalex.org/W2962814013","https://openalex.org/W2963318081","https://openalex.org/W2982464076","https://openalex.org/W2998045710","https://openalex.org/W3015636663","https://openalex.org/W3038022836","https://openalex.org/W3047304572","https://openalex.org/W3093034895","https://openalex.org/W3098486933","https://openalex.org/W3099980742","https://openalex.org/W3105122387","https://openalex.org/W3113075536","https://openalex.org/W4297687186","https://openalex.org/W4318619660","https://openalex.org/W6728757088"],"related_works":["https://openalex.org/W79913212","https://openalex.org/W2094884983","https://openalex.org/W2378898096","https://openalex.org/W560952460","https://openalex.org/W2290927522","https://openalex.org/W4283579741","https://openalex.org/W3066706303","https://openalex.org/W876159576","https://openalex.org/W2943612818","https://openalex.org/W1994346114"],"abstract_inverted_index":{"Federated":[0,188],"learning":[1],"(FL)":[2],"enables":[3],"resource-constrained":[4],"edge":[5],"nodes":[6,32,79,134],"to":[7,43,71,92,112,227,234,241],"collaboratively":[8],"learn":[9],"a":[10,17,57,157],"global":[11,94,119,148],"model":[12,34,73,95,120],"under":[13,75],"the":[14,76,85,89,93,101,118,139,142,147,185,220],"orchestration":[15],"of":[16,78,132,222],"central":[18],"server":[19],"while":[20],"keeping":[21],"privacy-sensitive":[22],"data":[23,28,98],"locally.":[24],"The":[25,130,163],"non-independent-and-identically-distributed":[26],"(non-IID)":[27],"samples":[29],"across":[30],"participating":[31,133],"slow":[33],"training":[35,128,213],"and":[36,97,106,146,151,199,207,232],"impose":[37],"additional":[38],"communication":[39,178,223],"rounds":[40,224],"for":[41,116],"FL":[42,212],"converge.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,209],"propose":[49,111],"<monospace":[50,54,58,64,191,215,242],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[51,55,59,65,192,216,243],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Fed</monospace>":[52],"erated":[53],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Ad</monospace>":[56],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">p</monospace>":[60],"tive":[61],"Weighting":[62],"(":[63,190],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">FedAdp</monospace>":[66,217],")":[67,194],"algorithm":[68],"that":[69,211],"aims":[70],"accelerate":[72],"convergence":[74],"presence":[77],"with":[80,214],"non-IID":[81],"dataset.":[82],"We":[83,109],"observe":[84],"implicit":[86],"connection":[87],"between":[88,141],"node":[90,103,123,173],"contribution":[91,124,131,174],"aggregation":[96],"distribution":[99],"on":[100,122,229,236],"local":[102,143],"through":[104,126],"theoretical":[105],"empirical":[107],"analysis.":[108],"then":[110],"assign":[113],"different":[114],"weights":[115],"updating":[117],"based":[121],"adaptively":[125],"each":[127],"round.":[129],"is":[135,154,195],"first":[136],"measured":[137],"by":[138,156,225],"angle":[140],"gradient":[144,149],"vector":[145],"vector,":[150],"then,":[152],"weight":[153],"quantified":[155],"designed":[158],"non-linear":[159],"mapping":[160],"function":[161],"subsequently.":[162],"simple":[164],"yet":[165],"effective":[166],"strategy":[167],"can":[168,218],"reinforce":[169],"positive":[170],"(suppress":[171],"negative)":[172],"dynamically,":[175],"resulting":[176],"in":[177,205],"round":[179],"reduction":[180],"drastically.":[181],"Its":[182],"superiority":[183],"over":[184],"commonly":[186],"adopted":[187],"Averaging":[189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">FedAvg</monospace>":[193,244],"verified":[196],"both":[197],"theoretically":[198],"experimentally.":[200],"With":[201],"extensive":[202],"experiments":[203],"performed":[204],"Pytorch":[206],"PySyft,":[208],"show":[210],"reduce":[219],"number":[221],"up":[226,233],"54.1%":[228],"MNIST":[230],"dataset":[231],"45.4%":[235],"FashionMNIST":[237],"dataset,":[238],"as":[239],"compared":[240],"algorithm.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":63},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}