{"id":"https://openalex.org/W3188200630","doi":"https://doi.org/10.1109/icc42927.2021.9500355","title":"Traffic Management for Distributed Machine Learning in RDMA-enabled Data Center Networks","display_name":"Traffic Management for Distributed Machine Learning in RDMA-enabled Data Center Networks","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3188200630","doi":"https://doi.org/10.1109/icc42927.2021.9500355","mag":"3188200630"},"language":"en","primary_location":{"id":"doi:10.1109/icc42927.2021.9500355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc42927.2021.9500355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2021 - IEEE International Conference on 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/A5103078129","display_name":"Weihong Yang","orcid":"https://orcid.org/0000-0003-4981-0381"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weihong Yang","raw_affiliation_strings":["Department of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052758633","display_name":"Yang Qin","orcid":"https://orcid.org/0000-0002-1981-1423"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Qin","raw_affiliation_strings":["Department of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026700823","display_name":"Zukai Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zukai Jiang","raw_affiliation_strings":["Department of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103078129"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.12993048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.9988999962806702,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9986000061035156,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8508740067481995},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.7038546800613403},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6175646781921387},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5127326250076294},{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.5031730532646179},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.493722528219223},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4348006248474121},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4342005252838135},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.43151962757110596},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.42866426706314087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14146128296852112},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14011642336845398}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8508740067481995},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.7038546800613403},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6175646781921387},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5127326250076294},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.5031730532646179},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.493722528219223},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4348006248474121},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4342005252838135},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.43151962757110596},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.42866426706314087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14146128296852112},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14011642336845398},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icc42927.2021.9500355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc42927.2021.9500355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2021 - IEEE International Conference on Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-161845","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-161845","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2036003010","https://openalex.org/W2045271686","https://openalex.org/W2057344983","https://openalex.org/W2117884704","https://openalex.org/W2132737349","https://openalex.org/W2137152139","https://openalex.org/W2158733823","https://openalex.org/W2296319761","https://openalex.org/W2339765813","https://openalex.org/W2343556076","https://openalex.org/W2498764059","https://openalex.org/W2524428287","https://openalex.org/W2617766261","https://openalex.org/W2769644379","https://openalex.org/W2774000609","https://openalex.org/W2824027552","https://openalex.org/W2919632853","https://openalex.org/W2920397365","https://openalex.org/W2962758826","https://openalex.org/W2963149401","https://openalex.org/W2963786636","https://openalex.org/W2963803379","https://openalex.org/W2964004663","https://openalex.org/W2972362103","https://openalex.org/W2975712713","https://openalex.org/W2982475424","https://openalex.org/W3047357290","https://openalex.org/W3107997909","https://openalex.org/W4232284301","https://openalex.org/W4250589301","https://openalex.org/W6679393576","https://openalex.org/W6727208969","https://openalex.org/W6738460352","https://openalex.org/W6739693220","https://openalex.org/W6746200960","https://openalex.org/W6746839373","https://openalex.org/W6786232625"],"related_works":["https://openalex.org/W3090586438","https://openalex.org/W2782433361","https://openalex.org/W2416075414","https://openalex.org/W2475302168","https://openalex.org/W4366999533","https://openalex.org/W2134569538","https://openalex.org/W3198746232","https://openalex.org/W4365450377","https://openalex.org/W4245217724","https://openalex.org/W2907568399"],"abstract_inverted_index":{"It":[0],"has":[1,96],"become":[2],"a":[3,14,41,51,68,92,100],"common":[4],"practice":[5],"to":[6,55,71,166,185,246],"train":[7],"large":[8],"machine":[9],"learning":[10],"(ML)":[11],"models":[12],"across":[13],"cluster":[15],"of":[16,34,87,134,159,199,209,230,248],"computing":[17],"nodes":[18],"connected":[19],"by":[20,28,49,212],"RDMA-enabled":[21],"networks.":[22],"However,":[23],"the":[24,32,72,104,132,152,157,168,176,181,187,191,207,249],"communication":[25],"overhead":[26],"caused":[27],"parameter":[29,221],"synchronization":[30,222],"deteriorates":[31],"performance":[33,124,208],"such":[35],"distributed":[36],"ML":[37],"(DML),":[38],"especially":[39],"in":[40,91,103,119,127,151,223],"large-scale":[42],"setting.":[43],"This":[44],"paper":[45],"tackles":[46],"this":[47],"issue":[48],"developing":[50],"traffic":[52,150,228],"management":[53],"scheme":[54,77],"support":[56],"DML":[57,88,109,118,137,149],"traffic,":[58],"called":[59],"TMDML":[60,200],"(Traffic":[61],"Management":[62],"for":[63,148,201],"DML),":[64],"which":[65],"needs":[66],"only":[67,84],"minor":[69],"modification":[70],"existing":[73],"RDMA":[74],"congestion":[75],"control":[76],"DCQCN.":[78,217],"We":[79,129,205,218],"assume":[80],"that":[81,98,126,144],"there":[82],"is":[83,146],"one":[85],"instance":[86],"workload":[89],"running":[90],"network.":[93],"Existing":[94],"literature":[95],"shown":[97],"Fat-Tree,":[99],"predominant":[101],"topology":[102],"data":[105],"center,":[106],"poorly":[107],"supports":[108],"compared":[110],"with":[111,216,227],"BCube.":[112,128],"With":[113],"our":[114,210],"proposed":[115],"TMDML,":[116],"training":[117],"Fat-Tree":[120,224],"can":[121,243],"achieve":[122,244],"better":[123],"than":[125],"first":[130],"study":[131],"impact":[133,158],"multi-bottlenecks":[135,153],"on":[136],"via":[138],"NS-3-based":[139],"simulations.":[140],"The":[141],"results":[142],"show":[143],"DCQCN":[145],"inefficient":[147],"scenario.":[154],"To":[155],"mitigate":[156],"multi-bottlenecks,":[160],"we":[161,194],"propose":[162],"an":[163],"optimization":[164,183],"model":[165],"minimize":[167],"maximum":[169],"flow":[170],"completion":[171],"time":[172,250],"(FCT)":[173],"while":[174],"stabilizing":[175],"queues,":[177],"and":[178,225,239],"then":[179],"apply":[180],"Lyapunov":[182],"technique":[184],"solve":[186],"problem.":[188],"For":[189],"all":[190],"practical":[192],"purposes,":[193],"present":[195],"two":[196],"heuristic":[197],"implementations":[198],"different":[202],"deployment":[203],"requirements.":[204],"evaluate":[206],"proposals":[211,242],"simulation,":[213],"comparing":[214],"it":[215],"use":[219],"All-Reduce":[220],"BCube":[226],"trace":[229],"modern":[231],"deep":[232],"neural":[233],"network":[234],"models,":[235],"including":[236],"AlexNet,":[237],"ResNet50,":[238],"VGG-16.":[240],"Our":[241],"up":[245],"59%":[247],"reduction.":[251]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}