{"id":"https://openalex.org/W3047304572","doi":"https://doi.org/10.1109/infocom41043.2020.9155494","title":"Optimizing Federated Learning on Non-IID Data with Reinforcement Learning","display_name":"Optimizing Federated Learning on Non-IID Data with Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3047304572","doi":"https://doi.org/10.1109/infocom41043.2020.9155494","mag":"3047304572"},"language":"en","primary_location":{"id":"doi:10.1109/infocom41043.2020.9155494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom41043.2020.9155494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","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/A5100649232","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-6956-7342"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hao Wang","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082189841","display_name":"Zakhary Kaplan","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zakhary Kaplan","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032424832","display_name":"Di Niu","orcid":"https://orcid.org/0000-0002-5250-7327"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Di Niu","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083596391","display_name":"Baochun Li","orcid":"https://orcid.org/0000-0003-2404-0974"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Baochun Li","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100649232"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":68.9159,"has_fulltext":false,"cited_by_count":938,"citation_normalized_percentile":{"value":0.99936237,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1698","last_page":"1707"},"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":0.9901999831199646,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8646912574768066},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6790130734443665},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6566287875175476},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.5885757803916931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580585241317749},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.573891818523407},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.569685697555542},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.546384334564209},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5319300889968872},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4713422954082489},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4468046724796295},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42438217997550964},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10565134882926941},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09545058012008667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8646912574768066},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6790130734443665},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6566287875175476},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.5885757803916931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580585241317749},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.573891818523407},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.569685697555542},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.546384334564209},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5319300889968872},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4713422954082489},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4468046724796295},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42438217997550964},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10565134882926941},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09545058012008667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom41043.2020.9155494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom41043.2020.9155494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","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":38,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2116612304","https://openalex.org/W2121863487","https://openalex.org/W2155968351","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2546571074","https://openalex.org/W2617411258","https://openalex.org/W2746553466","https://openalex.org/W2767079719","https://openalex.org/W2774000609","https://openalex.org/W2774918944","https://openalex.org/W2798720628","https://openalex.org/W2807006176","https://openalex.org/W2904190483","https://openalex.org/W2912592113","https://openalex.org/W2962688627","https://openalex.org/W2963300197","https://openalex.org/W2963803379","https://openalex.org/W2963902936","https://openalex.org/W2989289980","https://openalex.org/W3038028469","https://openalex.org/W3105122387","https://openalex.org/W4214717370","https://openalex.org/W4297687186","https://openalex.org/W4298857966","https://openalex.org/W4300427714","https://openalex.org/W4318619660","https://openalex.org/W6728757088","https://openalex.org/W6738144653","https://openalex.org/W6738383168","https://openalex.org/W6746839373","https://openalex.org/W6747231328","https://openalex.org/W6752029299","https://openalex.org/W6757172675","https://openalex.org/W6758757267","https://openalex.org/W6759226220","https://openalex.org/W6760157594"],"related_works":["https://openalex.org/W2944823289","https://openalex.org/W3037018281","https://openalex.org/W2972592048","https://openalex.org/W2358319515","https://openalex.org/W4321854979","https://openalex.org/W4323521275","https://openalex.org/W4385893187","https://openalex.org/W3169941283","https://openalex.org/W4388282301","https://openalex.org/W4385625427"],"abstract_inverted_index":{"The":[0],"widespread":[1],"deployment":[2],"of":[3,18,62,106,130,160,207,221,228,243],"machine":[4],"learning":[5,71,132,249],"applications":[6],"in":[7,13,82,127,209,236,247],"ubiquitous":[8],"environments":[9],"has":[10,30],"sparked":[11],"interests":[12],"exploiting":[14],"the":[15,48,58,102,122,135,158,167,180,219,226,241,258,271],"vast":[16],"amount":[17],"data":[19,26,85,140,162,181],"stored":[20],"on":[21,43,78,163,172,183,187,198,257,262,266],"mobile":[22,63],"devices.":[23],"To":[24],"preserve":[25],"privacy,":[27],"Federated":[28,272],"Learning":[29],"been":[31],"proposed":[32],"to":[33,57,72,101,125,133,142,178,203,213,255,270],"learn":[34],"a":[35,52,164,195,205,215],"shared":[36],"model":[37,74,168,190],"by":[38,138,253],"performing":[39],"distributed":[40,96],"training":[41,161],"locally":[42],"participating":[44,80],"devices":[45,81,89,124,208],"and":[46,76,94,104,141,149,166,224,264],"aggregating":[47],"local":[49],"models":[50],"into":[51],"global":[53],"one.":[54],"However,":[55],"due":[56],"limited":[59],"network":[60],"connectivity":[61],"devices,":[64],"it":[65],"is":[66],"not":[67,92],"practical":[68],"for":[69],"federated":[70,107,131,248],"perform":[73],"updates":[75],"aggregation":[77],"all":[79,88],"parallel.":[83],"Besides,":[84],"samples":[86],"across":[87],"are":[90],"usually":[91],"independent":[93],"identically":[95],"(IID),":[97],"posing":[98],"additional":[99],"challenges":[100],"convergence":[103],"speed":[105,143],"learning.":[108],"In":[109],"this":[110],"paper,":[111],"we":[112,152,238],"propose":[113,194],"Favor,":[114],"an":[115,154],"experience-driven":[116],"control":[117],"framework":[118],"that":[119,184,201,217,240],"intelligently":[120],"chooses":[121],"client":[123],"participate":[126],"each":[128,210],"round":[129,212],"counterbalance":[134],"bias":[136],"introduced":[137],"non-IID":[139],"up":[144,254],"convergence.":[145],"Through":[146],"both":[147],"empirical":[148],"mathematical":[150],"analysis,":[151],"observe":[153],"implicit":[155],"connection":[156],"between":[157],"distribution":[159,182],"device":[165,185],"weights":[169],"trained":[170],"based":[171,186,197],"those":[173],"data,":[174],"which":[175],"enables":[176],"us":[177],"profile":[179],"its":[188],"uploaded":[189],"weights.":[191],"We":[192],"then":[193],"mechanism":[196],"deep":[199],"Q-learning":[200],"learns":[202],"select":[204],"subset":[206],"communication":[211,230,244],"maximize":[214],"reward":[216],"encourages":[218],"increase":[220],"validation":[222],"accuracy":[223],"penalizes":[225],"use":[227],"more":[229],"rounds.":[231],"With":[232],"extensive":[233],"experiments":[234],"performed":[235],"PyTorch,":[237],"show":[239],"number":[242],"rounds":[245],"required":[246],"can":[250],"be":[251],"reduced":[252],"49%":[256],"MNIST":[259],"dataset,":[260],"23%":[261],"FashionMNIST,":[263],"42%":[265],"CIFAR-10,":[267],"as":[268],"compared":[269],"Averaging":[273],"algorithm.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":170},{"year":2024,"cited_by_count":239},{"year":2023,"cited_by_count":221},{"year":2022,"cited_by_count":156},{"year":2021,"cited_by_count":120},{"year":2020,"cited_by_count":10}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}