{"id":"https://openalex.org/W4392309097","doi":"https://doi.org/10.1109/tc.2024.3371794","title":"UniSched: A Unified Scheduler for Deep Learning Training Jobs With Different User Demands","display_name":"UniSched: A Unified Scheduler for Deep Learning Training Jobs With Different User Demands","publication_year":2024,"publication_date":"2024-02-29","ids":{"openalex":"https://openalex.org/W4392309097","doi":"https://doi.org/10.1109/tc.2024.3371794"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3371794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3371794","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","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/A5100732619","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0002-7048-1722"},"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":"Wei Gao","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7048-1722","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103041352","display_name":"Zhisheng Ye","orcid":"https://orcid.org/0000-0002-4568-0244"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisheng Ye","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4568-0244","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614087","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0001-8456-0491"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["Shanghai AI Lab &#x0026; SenseTime, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8456-0491","affiliations":[{"raw_affiliation_string":"Shanghai AI Lab &#x0026; SenseTime, Beijing, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101591101","display_name":"Tianwei Zhang","orcid":"https://orcid.org/0000-0001-6595-6650"},"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":"Tianwei Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6595-6650","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041572550","display_name":"Yonggang Wen","orcid":"https://orcid.org/0000-0002-2751-5114"},"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":["School of Computer Science and Engineering, Nanyang Technological University, Singapore","S-Lab, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2751-5114","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7562,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.95916537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"73","issue":"6","first_page":"1500","last_page":"1515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9929999709129333,"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":0.9929999709129333,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9914000034332275,"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/T12288","display_name":"Optimization and Search Problems","score":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7802273035049438},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6413449048995972},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4459637701511383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4229172468185425},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.09007221460342407},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07447957992553711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802273035049438},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6413449048995972},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4459637701511383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4229172468185425},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.09007221460342407},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07447957992553711},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2024.3371794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3371794","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","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":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1914323026","display_name":null,"funder_award_id":"2022ZD0160201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2137726616","https://openalex.org/W2335814492","https://openalex.org/W2342761116","https://openalex.org/W2798515322","https://openalex.org/W2799240483","https://openalex.org/W2883265831","https://openalex.org/W2926767350","https://openalex.org/W2949676527","https://openalex.org/W2962725887","https://openalex.org/W2962747323","https://openalex.org/W2964667342","https://openalex.org/W2987954639","https://openalex.org/W3010528756","https://openalex.org/W3012536640","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3101708369","https://openalex.org/W3108033633","https://openalex.org/W3118608800","https://openalex.org/W3136172274","https://openalex.org/W3159050454","https://openalex.org/W3209503812","https://openalex.org/W4205916020","https://openalex.org/W4221141126","https://openalex.org/W4319068657","https://openalex.org/W6693270258","https://openalex.org/W6694517276","https://openalex.org/W6753505025","https://openalex.org/W6756009870","https://openalex.org/W6758283263","https://openalex.org/W6759814162","https://openalex.org/W6769424276","https://openalex.org/W6778883912","https://openalex.org/W6781728138","https://openalex.org/W6782839094","https://openalex.org/W6784871562","https://openalex.org/W6785115463","https://openalex.org/W6787972765","https://openalex.org/W6801004768","https://openalex.org/W6809572605"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"The":[0],"growth":[1],"of":[2,25,63,87,94,100,156,166,177,192],"deep":[3,15],"learning":[4,16],"training":[5],"(DLT)":[6],"jobs":[7,128,158,168],"in":[8,187],"modern":[9],"GPU":[10,42],"clusters":[11],"calls":[12],"for":[13,33,40,119,126],"efficient":[14],"(DL)":[17],"scheduler":[18,82],"designs.":[19],"Due":[20],"to":[21,44,83,145,161,171],"the":[22,92,98,121,137,141,152,164,175],"extensive":[23],"applications":[24],"DL":[26,57],"technology,":[27],"developers":[28],"may":[29],"have":[30],"different":[31,85,106],"demands":[32,48],"their":[34],"DLT":[35,53],"jobs.":[36,54],"It":[37],"is":[38],"important":[39],"a":[41,80,183,188],"cluster":[43,190],"support":[45],"all":[46],"these":[47],"and":[49,66,124,129,163,181],"efficiently":[50],"execute":[51],"those":[52,64],"Unfortunately,":[55],"existing":[56],"schedulers":[58],"mainly":[59],"focus":[60],"on":[61,185],"part":[62],"demands,":[65],"cannot":[67],"provide":[68],"comprehensive":[69],"scheduling":[70,88],"services.":[71],"<p":[72],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[73],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">In":[74],"this":[75],"work,":[76],"we":[77,179],"present":[78],"U<small>ni</small>S<small>ched</small>,":[79,178],"unified":[81],"optimize":[84],"types":[86],"objectives":[89],"(e.g.,":[90,110],"guaranteeing":[91],"deadlines":[93],"SLO":[95,157],"jobs,":[96],"minimizing":[97],"latency":[99,165],"best-effort":[101,167],"jobs).":[102],"Meanwhile,":[103],"U<small>ni</small>S<small>ched</small>":[104,148],"supports":[105],"job":[107,122,138],"stopping":[108],"criteria":[109],"iteration-based,":[111],"performance-based).":[112],"UniSched":[113],"includes":[114],"two":[115],"key":[116],"components:":[117],"Estimator":[118],"estimating":[120],"duration,":[123],"Selector":[125],"selecting":[127],"allocating":[130],"resources.":[131],"We":[132],"perform":[133],"large-scale":[134],"simulations":[135],"over":[136],"traces":[139],"from":[140],"production":[142],"clusters.":[143],"Compared":[144],"state-of-the-art":[146],"schedulers,":[147],"can":[149],"significantly":[150],"decrease":[151],"deadline":[153],"miss":[154],"rate":[155],"by":[159,169],"up":[160,170],"6.84\u00d7,":[162],"4.02\u00d7,":[172],"To":[173],"demonstrate":[174],"practicality":[176],"implement":[180],"deploy":[182],"prototype":[184],"Kubernetes":[186],"physical":[189],"consisting":[191],"64":[193],"GPUs.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}