{"id":"https://openalex.org/W4221149636","doi":"https://doi.org/10.1109/infocom48880.2022.9796785","title":"GADGET: Online Resource Optimization for Scheduling Ring-All-Reduce Learning Jobs","display_name":"GADGET: Online Resource Optimization for Scheduling Ring-All-Reduce Learning Jobs","publication_year":2022,"publication_date":"2022-05-02","ids":{"openalex":"https://openalex.org/W4221149636","doi":"https://doi.org/10.1109/infocom48880.2022.9796785"},"language":"en","primary_location":{"id":"doi:10.1109/infocom48880.2022.9796785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom48880.2022.9796785","pdf_url":null,"source":{"id":"https://openalex.org/S4363607980","display_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","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":"IEEE INFOCOM 2022 - 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/A5031558801","display_name":"Menglu Yu","orcid":"https://orcid.org/0000-0002-3653-3453"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Menglu Yu","raw_affiliation_strings":["Iowa State University,Department of Computer Science","Department of Computer Science, Iowa State University"],"affiliations":[{"raw_affiliation_string":"Iowa State University,Department of Computer Science","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Computer Science, Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883909","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0001-9085-6280"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":["Iowa State University,Department of Computer Science","Department of Computer Science, Iowa State University"],"affiliations":[{"raw_affiliation_string":"Iowa State University,Department of Computer Science","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Computer Science, Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040279482","display_name":"Bo Ji","orcid":"https://orcid.org/0000-0003-0149-7509"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Ji","raw_affiliation_strings":["Virginia Tech,Department of Computer Science","Department of Computer Science, Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012597518","display_name":"Chuan Wu","orcid":"https://orcid.org/0000-0002-3144-4398"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chuan Wu","raw_affiliation_strings":["The University of Hong Kong,Department of Computer Science","Department of Computer Science, The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Computer Science","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059626072","display_name":"Hridesh Rajan","orcid":"https://orcid.org/0000-0002-9410-9562"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hridesh Rajan","raw_affiliation_strings":["Iowa State University,Department of Computer Science","Department of Computer Science, Iowa State University"],"affiliations":[{"raw_affiliation_string":"Iowa State University,Department of Computer Science","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Computer Science, Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409661","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0001-8844-3233"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]},{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["The Ohio State University,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, The Ohio State University","Department of Computer Science, Iowa State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science, Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031558801"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":4.8158,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.95997713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1569","last_page":"1578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9977999925613403,"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":0.8272351026535034},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7231490612030029},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6782622337341309},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.662462592124939},{"id":"https://openalex.org/keywords/gadget","display_name":"Gadget","score":0.6167199015617371},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5470446348190308},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.4142359495162964},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2649320363998413},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.15714818239212036},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15419381856918335},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14279338717460632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272351026535034},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7231490612030029},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6782622337341309},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.662462592124939},{"id":"https://openalex.org/C119770614","wikidata":"https://www.wikidata.org/wiki/Q5516347","display_name":"Gadget","level":2,"score":0.6167199015617371},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5470446348190308},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.4142359495162964},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2649320363998413},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.15714818239212036},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15419381856918335},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14279338717460632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom48880.2022.9796785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom48880.2022.9796785","pdf_url":null,"source":{"id":"https://openalex.org/S4363607980","display_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","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":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1525444182","https://openalex.org/W1993982015","https://openalex.org/W2018162709","https://openalex.org/W2028242525","https://openalex.org/W2031904783","https://openalex.org/W2060393849","https://openalex.org/W2105947650","https://openalex.org/W2129542763","https://openalex.org/W2132651631","https://openalex.org/W2163961697","https://openalex.org/W2189465200","https://openalex.org/W2609354095","https://openalex.org/W2614112306","https://openalex.org/W2760837370","https://openalex.org/W2809420642","https://openalex.org/W2915497091","https://openalex.org/W2919594608","https://openalex.org/W2949092636","https://openalex.org/W2953384591","https://openalex.org/W2962684017","https://openalex.org/W2963149401","https://openalex.org/W2963973986","https://openalex.org/W2988221399","https://openalex.org/W2988480584","https://openalex.org/W2992672771","https://openalex.org/W3047537431","https://openalex.org/W3102385572","https://openalex.org/W4288289123","https://openalex.org/W4295312788","https://openalex.org/W4301239768","https://openalex.org/W6628377381","https://openalex.org/W6665801690","https://openalex.org/W6684084819","https://openalex.org/W6687322159","https://openalex.org/W6713134421","https://openalex.org/W6748645090","https://openalex.org/W6752199355","https://openalex.org/W6759814162","https://openalex.org/W6763733944","https://openalex.org/W6766978945","https://openalex.org/W6769424276","https://openalex.org/W6771327545"],"related_works":["https://openalex.org/W4252293060","https://openalex.org/W4212943538","https://openalex.org/W2475971442","https://openalex.org/W4312756098","https://openalex.org/W3194202522","https://openalex.org/W4319586723","https://openalex.org/W2895982276","https://openalex.org/W2039885954","https://openalex.org/W1981130628","https://openalex.org/W3204654320"],"abstract_inverted_index":{"Fueled":[0],"by":[1,87],"advances":[2],"in":[3,34,77,102,127],"distributed":[4,35,157],"deep":[5,118],"learning":[6],"(DDL),":[7],"recent":[8],"years":[9],"have":[10],"witnessed":[11],"a":[12,59,89,110,122,163],"rapidly":[13],"growing":[14],"demand":[15],"for":[16,50,71,96,116],"resource-intensive":[17],"distributed/parallel":[18],"computing":[19,23,78],"to":[20,46,66,83,174],"process":[21],"DDL":[22,75,98,128],"jobs.":[24,99],"To":[25,54],"resolve":[26],"network":[27],"communication":[28],"bottleneck":[29],"and":[30,182],"load":[31],"balancing":[32],"issues":[33],"computing,":[36],"the":[37,48,141,176,179,186,189],"so-called":[38],"\"ring-all-reduce\"":[39],"decentralized":[40],"architecture":[41],"has":[42],"been":[43],"increasingly":[44],"adopted":[45],"remove":[47],"need":[49],"dedicated":[51],"parameter":[52],"servers.":[53],"date,":[55],"however,":[56],"there":[57],"remains":[58],"lack":[60],"of":[61,91,125,178,188],"theoretical":[62],"understanding":[63],"on":[64,140],"how":[65],"design":[67],"resource":[68,93,112,150],"optimization":[69,130],"algorithms":[70],"efficiently":[72],"scheduling":[73,94,113,151],"ring-all-reduce":[74,97,117,156],"jobs":[76],"clusters.":[79],"This":[80],"motivates":[81],"us":[82],"fill":[84],"this":[85,103],"gap":[86],"proposing":[88],"series":[90],"new":[92,111],"designs":[95],"Our":[100],"contributions":[101],"paper":[104],"are":[105],"threefold:":[106],"i)":[107],"We":[108,169],"propose":[109],"analytical":[114,144],"model":[115],"learning,":[119],"which":[120,161],"covers":[121],"wide":[123],"range":[124],"objectives":[126],"performance":[129,143,166],"(e.g.,":[131],"excessive":[132],"training":[133],"avoidance,":[134],"energy":[135],"efficiency,":[136],"fairness);":[137],"ii)":[138],"Based":[139],"proposed":[142],"model,":[145],"we":[146],"develop":[147],"an":[148],"efficient":[149],"algorithm":[152],"called":[153],"GADGET":[154,180],"(greedy":[155],"graph":[158],"embedding":[159],"technique),":[160],"enjoys":[162],"provable":[164],"strong":[165],"guarantee;":[167],"iii)":[168],"conduct":[170],"extensive":[171],"trace-driven":[172],"experiments":[173],"demonstrate":[175],"effectiveness":[177],"approach":[181],"its":[183],"superiority":[184],"over":[185],"state":[187],"art.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
