{"id":"https://openalex.org/W2609354095","doi":"https://doi.org/10.1109/smartcomp.2017.7947053","title":"Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach","display_name":"Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2609354095","doi":"https://doi.org/10.1109/smartcomp.2017.7947053","mag":"2609354095"},"language":"en","primary_location":{"id":"doi:10.1109/smartcomp.2017.7947053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartcomp.2017.7947053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Smart Computing (SMARTCOMP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1704.06738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yonggang Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yonggang Wen","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nguyen Binh Duong Ta","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nguyen Binh Duong Ta","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shengen Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengen Yan","raw_affiliation_strings":["Sensetime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sensetime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3735,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91059522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9947999715805054,"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/partition","display_name":"Partition (number theory)","score":0.7910000085830688},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.6110000014305115},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5856000185012817},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5687000155448914},{"id":"https://openalex.org/keywords/virtualization","display_name":"Virtualization","score":0.5479000210762024},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4262000024318695},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.4059999883174896},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.40529999136924744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440999984741211},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7910000085830688},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7057999968528748},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.6110000014305115},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.5479000210762024},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C2778710394","wikidata":"https://www.wikidata.org/wiki/Q4179813","display_name":"Live migration","level":4,"score":0.3479999899864197},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.337799996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C3739613","wikidata":"https://www.wikidata.org/wiki/Q679003","display_name":"Distributed Computing Environment","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2778274720","wikidata":"https://www.wikidata.org/wiki/Q7315806","display_name":"Resource Management System","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C2777958785","wikidata":"https://www.wikidata.org/wiki/Q17120940","display_name":"Resource efficiency","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/smartcomp.2017.7947053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartcomp.2017.7947053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Smart Computing (SMARTCOMP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.06738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.06738","pdf_url":"https://arxiv.org/pdf/1704.06738","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1704.06738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.06738","pdf_url":"https://arxiv.org/pdf/1704.06738","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1998234836","https://openalex.org/W2102849319","https://openalex.org/W2105947650","https://openalex.org/W2120422789","https://openalex.org/W2143853136","https://openalex.org/W2155893237","https://openalex.org/W2157954477","https://openalex.org/W2160121678","https://openalex.org/W2579247884","https://openalex.org/W4253241776","https://openalex.org/W6628558282","https://openalex.org/W6628701632","https://openalex.org/W6639249596","https://openalex.org/W6680929869","https://openalex.org/W6684084819","https://openalex.org/W6686509673","https://openalex.org/W6691209370","https://openalex.org/W6713134421"],"related_works":[],"abstract_inverted_index":{"Many":[0],"cluster":[1,12,59],"management":[2,60],"systems":[3],"(CMSs)":[4],"have":[5],"been":[6],"proposed":[7],"to":[8,73,134,145,159,162],"share":[9],"a":[10,51,57,75,130,141,155],"single":[11],"with":[13],"multiple":[14],"distributed":[15,26,151],"computing":[16],"systems.":[17],"However,":[18],"none":[19],"of":[20,132,143,157],"the":[21,32,69,103,126,137],"existing":[22,163],"approaches":[23],"can":[24,83],"handle":[25],"machine":[27],"learning":[28],"(ML)":[29],"workloads":[30],"given":[31],"following":[33],"criteria:":[34],"high":[35],"resource":[36,39,92,127],"utilization,":[37],"fair":[38],"allocation":[40],"and":[41,62,82,94,147],"low":[42],"sharing":[43,115,166],"overhead.":[44,116],"To":[45],"solve":[46],"this":[47],"problem,":[48],"we":[49],"propose":[50],"new":[52],"CMS":[53],"named":[54],"Dorm,":[55],"incorporating":[56],"dynamically-partitioned":[58],"mechanism":[61],"an":[63],"utilization-fairness":[64],"optimizer.":[65],"Specifically,":[66],"Dorm":[67,112,122],"uses":[68],"container-based":[70],"virtualization":[71],"technique":[72],"partition":[74,87,105],"cluster,":[76],"runs":[77],"one":[78],"application":[79,89,97],"per":[80],"partition,":[81],"dynamically":[84],"resize":[85],"each":[86],"at":[88],"runtime":[90],"for":[91,108],"efficiency":[93],"fairness.":[95],"Each":[96],"directly":[98],"launches":[99],"its":[100],"tasks":[101],"on":[102],"assigned":[104],"without":[106],"petitioning":[107],"resources":[109],"frequently,":[110],"so":[111],"imposes":[113],"flat":[114],"Extensive":[117],"performance":[118],"evaluations":[119],"showed":[120],"that":[121],"could":[123],"simultaneously":[124],"increase":[125],"utilization":[128],"by":[129,140,154],"factor":[131,142,156],"up":[133,144,149,158],"2.32,":[135],"reduce":[136],"fairness":[138],"loss":[139],"1.52,":[146],"speed":[148],"popular":[150],"ML":[152],"applications":[153],"2.72,":[160],"compared":[161],"approaches.":[164],"Dorm's":[165],"overhead":[167],"is":[168],"less":[169],"than":[170],"5%":[171],"in":[172],"most":[173],"cases.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2017-05-05T00:00:00"}