{"id":"https://openalex.org/W4416323641","doi":"https://doi.org/10.1109/tmc.2025.3634217","title":"Sculpting Resource Efficiency: Diffusion Model-Aided Dynamic Multi-Job Scheduling With Topology Awareness in AI Clusters","display_name":"Sculpting Resource Efficiency: Diffusion Model-Aided Dynamic Multi-Job Scheduling With Topology Awareness in AI Clusters","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W4416323641","doi":"https://doi.org/10.1109/tmc.2025.3634217"},"language":null,"primary_location":{"id":"doi:10.1109/tmc.2025.3634217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3634217","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","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/A5041093581","display_name":"Meng Yuan","orcid":"https://orcid.org/0000-0002-6328-4413"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yuan","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6328-4413","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080619339","display_name":"Songjing Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songjing Tao","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755664","display_name":"Qiang Wu","orcid":"https://orcid.org/0000-0002-9467-1491"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-9467-1491","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033047253","display_name":"Xinzi Wang","orcid":"https://orcid.org/0009-0007-3279-8669"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbin Wang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-3279-8669","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447486","display_name":"Ran Wang","orcid":"https://orcid.org/0000-0001-5601-0513"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]},{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Wang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","College of Computer and Data Science, Fuzhou University, China"],"raw_orcid":"https://orcid.org/0000-0001-5601-0513","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"College of Computer and Data Science, Fuzhou University, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003317644","display_name":"Jie Hao","orcid":"https://orcid.org/0000-0002-1269-2097"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hao","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1269-2097","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091266202","display_name":"Dusit Niyato","orcid":"https://orcid.org/0000-0002-7442-7416"},"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":"Dusit Niyato","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7442-7416","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35822796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"4","first_page":"5872","last_page":"5889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.1940000057220459,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.1940000057220459,"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":0.10409999638795853,"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":0.09790000319480896,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6444000005722046},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.5645999908447266},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5307000279426575},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5293999910354614},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.4968000054359436},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.4099999964237213},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.3538999855518341},{"id":"https://openalex.org/keywords/round-robin-scheduling","display_name":"Round-robin scheduling","score":0.33329999446868896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8734999895095825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7462999820709229},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.5645999908447266},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.4968000054359436},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.4099999964237213},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C175893541","wikidata":"https://www.wikidata.org/wiki/Q1196582","display_name":"Round-robin scheduling","level":4,"score":0.33329999446868896},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C112866106","wikidata":"https://www.wikidata.org/wiki/Q267053","display_name":"Lottery scheduling","level":5,"score":0.32010000944137573},{"id":"https://openalex.org/C119948110","wikidata":"https://www.wikidata.org/wiki/Q7858726","display_name":"Two-level scheduling","level":4,"score":0.3000999987125397},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C159022435","wikidata":"https://www.wikidata.org/wiki/Q5532874","display_name":"Genetic algorithm scheduling","level":5,"score":0.27000001072883606},{"id":"https://openalex.org/C2777958785","wikidata":"https://www.wikidata.org/wiki/Q17120940","display_name":"Resource efficiency","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2025.3634217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3634217","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2126105956","https://openalex.org/W2143381319","https://openalex.org/W2592843051","https://openalex.org/W2805210382","https://openalex.org/W2913662728","https://openalex.org/W2963020121","https://openalex.org/W2973229164","https://openalex.org/W2997546679","https://openalex.org/W2999347502","https://openalex.org/W3012125688","https://openalex.org/W3047537431","https://openalex.org/W3100789280","https://openalex.org/W3158864847","https://openalex.org/W3194065545","https://openalex.org/W3212845011","https://openalex.org/W4221149636","https://openalex.org/W4293153207","https://openalex.org/W4297882618","https://openalex.org/W4297964528","https://openalex.org/W4313186370","https://openalex.org/W4381735906","https://openalex.org/W4382998652","https://openalex.org/W4384786048","https://openalex.org/W4385627407","https://openalex.org/W4386280791","https://openalex.org/W4387195417","https://openalex.org/W4388240184","https://openalex.org/W4390263770","https://openalex.org/W4390872109","https://openalex.org/W4391019625","https://openalex.org/W4392152415","https://openalex.org/W4392901632","https://openalex.org/W4392910431","https://openalex.org/W4392927807","https://openalex.org/W4394745249","https://openalex.org/W4396817538","https://openalex.org/W4401017926","https://openalex.org/W4402577024","https://openalex.org/W4405114800","https://openalex.org/W4405710287","https://openalex.org/W4409282468","https://openalex.org/W4413756551"],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"adoption":[2],"of":[3,11,31,66,127,137,158,210],"AI-Generated":[4,171],"Content":[5],"(AIGC)":[6],"has":[7],"made":[8],"large-scale":[9],"processing":[10],"multiple":[12,67,106],"Generative":[13],"AI":[14],"(GAI)":[15],"training":[16,48,69,92,108,126],"jobs":[17,70,139,160],"a":[18,58,62,72,148,190],"key":[19],"strategy":[20],"for":[21,104],"improving":[22],"cost-efficiency":[23],"in":[24,47,51,71],"computing":[25,73],"clusters.":[26],"However,":[27],"the":[28,64,132,135,141,156,168,207,225,230],"distributed":[29,125],"nature":[30],"GAI":[32,68,107,128,159],"models,":[33],"together":[34],"with":[35,152,215],"inherent":[36],"network":[37,83,209],"bottlenecks,":[38],"imposes":[39],"significant":[40],"challenges":[41],"on":[42],"system":[43],"performance.":[44,93],"Moreover,":[45],"differences":[46],"purposes,":[49],"variations":[50],"model":[52],"sizes,":[53],"and":[54,82,90,123,140,161,182,221],"asynchronous":[55],"lifecycles":[56],"create":[57],"dynamic":[59],"environment.":[60],"As":[61],"result,":[63],"coexistence":[65],"cluster":[74],"exacerbates":[75],"problems":[76],"such":[77],"as":[78],"resource":[79,88,101,185,198],"misallocation,":[80],"fragmentation,":[81],"contention,":[84],"leading":[85],"to":[86,97,119,177,194,217],"low":[87],"utilization":[89],"inefficient":[91],"These":[94],"motivate":[95],"us":[96],"explore":[98],"an":[99,113],"efficient":[100,124],"scheduling":[102,116,122,186,202],"approach":[103],"completing":[105],"jobs.":[109],"Accordingly,":[110],"we":[111,146,205],"introduce":[112],"intrinsic":[114],"topology-aware":[115],"framework":[117],"designed":[118,176],"ensure":[120],"flexible":[121],"models.":[129],"To":[130],"address":[131,218],"trade-off":[133],"between":[134],"number":[136],"concurrent":[138],"communication":[142,163],"contention":[143],"they":[144],"generate,":[145],"formulate":[147],"multi-objective":[149],"optimization":[150],"problem":[151],"two":[153],"objectives:":[154],"maximizing":[155],"utility":[157],"minimizing":[162],"bandwidth.":[164],"We":[165],"then":[166],"propose":[167],"Diffusion":[169],"Model-based":[170],"Resources":[172],"Scheduling":[173],"(DARS)":[174],"algorithm,":[175],"capture":[178],"dynamic,":[179],"high-dimensional":[180],"environments":[181],"generate":[183],"optimal":[184],"decisions.":[187,203],"DARS":[188,216],"employs":[189],"denoising":[191],"diffusion":[192],"process":[193],"iteratively":[195],"refine":[196],"noisy":[197],"allocations":[199],"into":[200],"optimized":[201],"Subsequently,":[204],"replace":[206],"policy":[208],"Deep":[211],"Reinforcement":[212],"Learning":[213],"(DRL)":[214],"environmental":[219],"uncertainty":[220],"enhance":[222],"efficiency.":[223],"Finally,":[224],"simulation":[226],"results":[227],"confirm":[228],"that":[229],"proposed":[231],"algorithm":[232],"outperforms":[233],"existing":[234],"approaches.":[235]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-11-18T00:00:00"}