{"id":"https://openalex.org/W4386230822","doi":"https://doi.org/10.1109/tc.2023.3305753","title":"JointPS: Joint Parameter Server Placement and Flow Scheduling for Machine Learning Clusters","display_name":"JointPS: Joint Parameter Server Placement and Flow Scheduling for Machine Learning Clusters","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4386230822","doi":"https://doi.org/10.1109/tc.2023.3305753"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2023.3305753","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tc.2023.3305753","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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/A5075889174","display_name":"Yangming Zhao","orcid":"https://orcid.org/0000-0003-4194-3024"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yangming Zhao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576023","display_name":"Yang Cheng","orcid":"https://orcid.org/0009-0005-0503-874X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Yang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074187380","display_name":"Gongming Zhao","orcid":"https://orcid.org/0000-0003-1311-8908"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongming Zhao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101802512","display_name":"Yunfei Hou","orcid":"https://orcid.org/0000-0001-9443-4026"},"institutions":[{"id":"https://openalex.org/I43369023","display_name":"California State University, San Bernardino","ror":"https://ror.org/02n651896","country_code":"US","type":"education","lineage":["https://openalex.org/I43369023"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunfei Hou","raw_affiliation_strings":["California State University San Bernardino, San Bernardino, CA, USA"],"affiliations":[{"raw_affiliation_string":"California State University San Bernardino, San Bernardino, CA, USA","institution_ids":["https://openalex.org/I43369023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067164243","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0002-7223-8849"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["Software Engineering Institute, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Software Engineering Institute, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100728176","display_name":"Chunming Qiao","orcid":"https://orcid.org/0000-0002-4679-6572"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunming Qiao","raw_affiliation_strings":["University at Buffalo, The State University of New York, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"University at Buffalo, The State University of New York, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075889174"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.822,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88423833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"72","issue":"12","first_page":"3503","last_page":"3518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9975000023841858,"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":0.9890000224113464,"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":0.8352639675140381},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7390486598014832},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6170198917388916},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5396876335144043},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4345676898956299},{"id":"https://openalex.org/keywords/response-time","display_name":"Response time","score":0.42752206325531006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4199204444885254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3823767900466919},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36979103088378906},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20364907383918762},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1603865623474121},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11674562096595764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352639675140381},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7390486598014832},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6170198917388916},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5396876335144043},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4345676898956299},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.42752206325531006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4199204444885254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3823767900466919},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36979103088378906},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20364907383918762},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1603865623474121},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11674562096595764},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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":1,"locations":[{"id":"doi:10.1109/tc.2023.3305753","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tc.2023.3305753","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G3352484557","display_name":null,"funder_award_id":"62272428","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5047865717","display_name":null,"funder_award_id":"62202392","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6584702971","display_name":null,"funder_award_id":"BK20221261","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7392064758","display_name":null,"funder_award_id":"2208085MF167","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1545728916","https://openalex.org/W1584928512","https://openalex.org/W1686810756","https://openalex.org/W1698388015","https://openalex.org/W1850811203","https://openalex.org/W1968331080","https://openalex.org/W2005688170","https://openalex.org/W2046825771","https://openalex.org/W2060393849","https://openalex.org/W2110514750","https://openalex.org/W2130531694","https://openalex.org/W2149939304","https://openalex.org/W2166445532","https://openalex.org/W2194775991","https://openalex.org/W2469847610","https://openalex.org/W2559266308","https://openalex.org/W2564810971","https://openalex.org/W2617766261","https://openalex.org/W2618530766","https://openalex.org/W2769644379","https://openalex.org/W2789335636","https://openalex.org/W2794670651","https://openalex.org/W2798515322","https://openalex.org/W2899589750","https://openalex.org/W2962788286","https://openalex.org/W2963773265","https://openalex.org/W2975712713","https://openalex.org/W3035973338","https://openalex.org/W3036358974","https://openalex.org/W3091992486","https://openalex.org/W3118608800","https://openalex.org/W3124352525","https://openalex.org/W3130413249","https://openalex.org/W3195168961","https://openalex.org/W4224926627","https://openalex.org/W4237515752","https://openalex.org/W4285245070","https://openalex.org/W4288357791","https://openalex.org/W4289535786","https://openalex.org/W4292779060","https://openalex.org/W4298312531","https://openalex.org/W6637373629","https://openalex.org/W6738460352","https://openalex.org/W6746200960","https://openalex.org/W6747968877","https://openalex.org/W6751961731","https://openalex.org/W6754818105","https://openalex.org/W6762211661","https://openalex.org/W6778883912","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W1657880117","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2595172197","https://openalex.org/W1981130628","https://openalex.org/W2348635526","https://openalex.org/W2021864689","https://openalex.org/W2058728358"],"abstract_inverted_index":{"To":[0,28,135],"distill":[1],"more":[2,7],"information":[3],"from":[4],"training":[5,65,87,156,174],"data,":[6],"parameters":[8],"are":[9],"introduced":[10],"into":[11],"machine":[12,43,47],"learning":[13,44,48],"models.":[14],"As":[15],"a":[16,63,95],"result,":[17],"communication":[18,31],"becomes":[19],"the":[20,30,39,59,74,83,104,121,130,136,144,149,161,170,189],"bottleneck":[21],"of":[22,62,85,138,153,193],"Distributed":[23],"Machine":[24],"Learning":[25],"(DML)":[26],"systems.":[27],"alleviate":[29],"resource":[32],"contention":[33],"among":[34],"DML":[35,69,91,110,118,155,171,194],"jobs,":[36],"which":[37],"prolongs":[38],"time":[40,61,106,152,192],"to":[41,107,113,128,198],"train":[42],"models,":[45],"in":[46,53],"clusters,":[49],"JointPS":[50,56,101,116,141,186],"is":[51],"proposed":[52],"this":[54],"paper.":[55],"first":[57,145],"minimizes":[58,148],"completion":[60,133,151,191],"single":[64],"epoch":[66],"for":[67,89],"each":[68,90,109],"job":[70,92,132],"via":[71],"jointly":[72,159],"optimizing":[73,160],"parameter":[75,162],"server":[76,163],"placement":[77,164],"and":[78,81,165,173,180],"flow":[79,166],"scheduling,":[80],"predicts":[82],"number":[84],"remaining":[86,105],"epochs":[88],"by":[93,158,196],"leveraging":[94],"dynamic":[96],"model":[97],"fitting":[98],"method.":[99],"Then,":[100],"can":[102,187],"estimate":[103],"complete":[108],"job.":[111],"According":[112],"such":[114],"estimation,":[115],"schedules":[117],"jobs":[119,157,195],"following":[120],"Minimum":[122],"Remaining":[123],"Time":[124],"First":[125],"(MRTF)":[126],"principle":[127],"minimize":[129],"average":[131,150,190],"time.":[134],"best":[137],"our":[139],"knowledge,":[140],"should":[142],"be":[143],"work":[146],"that":[147,185],"network-intensive":[154],"scheduling":[167],"without":[168],"modifying":[169],"models":[172],"procedures.":[175],"Through":[176],"both":[177],"testbed":[178],"experiments":[179],"extensive":[181],"simulations,":[182],"we":[183],"demonstrate":[184],"reduce":[188],"up":[197],"88%":[199],"compared":[200],"with":[201],"state-of-the-art":[202],"technology.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}