{"id":"https://openalex.org/W7124155999","doi":"https://doi.org/10.1109/icpads67057.2025.11323091","title":"Efficient Scheduling for Multiple Distributed DNN Training Tasks in Resource-Constrained Edge Networks","display_name":"Efficient Scheduling for Multiple Distributed DNN Training Tasks in Resource-Constrained Edge Networks","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124155999","doi":"https://doi.org/10.1109/icpads67057.2025.11323091"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5120698113","display_name":"Zhiheng Tang","orcid":"https://orcid.org/0000-0002-3744-2254"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihang Tang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056669398","display_name":"Weiqi Yue","orcid":"https://orcid.org/0000-0001-7308-8347"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqi Yue","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012394991","display_name":"Baofu Wu","orcid":"https://orcid.org/0000-0003-0259-9427"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baofu Wu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084438189","display_name":"Bo Huang","orcid":"https://orcid.org/0000-0002-2404-2016"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Huang","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050753595","display_name":"Laiping Zhao","orcid":"https://orcid.org/0000-0003-1967-2192"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Laiping Zhao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123044658","display_name":"Keqiu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keqiu Li","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.55645604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5410000085830688,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5410000085830688,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.07530000060796738,"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":0.03840000182390213,"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":0.7050999999046326},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5235000252723694},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45829999446868896},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4334000051021576},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42010000348091125},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4059000015258789},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.38580000400543213},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.3612000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133000135421753},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7050999999046326},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5235000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506600022315979},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48179998993873596},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4334000051021576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4311000108718872},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42010000348091125},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.28209999203681946},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W7103816","https://openalex.org/W1525444182","https://openalex.org/W2080264349","https://openalex.org/W2143031615","https://openalex.org/W2145339207","https://openalex.org/W2150148016","https://openalex.org/W2371642549","https://openalex.org/W2798515322","https://openalex.org/W2962684017","https://openalex.org/W2964667342","https://openalex.org/W2968986602","https://openalex.org/W3094176367","https://openalex.org/W3144293453","https://openalex.org/W3195168961","https://openalex.org/W4229459129","https://openalex.org/W4285149049","https://openalex.org/W4378979503","https://openalex.org/W4386709668","https://openalex.org/W4387799594","https://openalex.org/W4390446475","https://openalex.org/W4400578856","https://openalex.org/W4400647474","https://openalex.org/W4401408814","https://openalex.org/W4402809029"],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"parameter":[2],"size":[3],"of":[4,45],"Deep":[5],"Neural":[6],"Networks":[7],"(DNNs)":[8],"has":[9,29],"significantly":[10],"enhanced":[11],"model":[12],"performance.":[13],"As":[14],"large-scale":[15],"DNN":[16,80,104],"models":[17],"typically":[18],"require":[19],"partitioning":[20],"into":[21,86],"multiple":[22,102],"blocks":[23],"for":[24,35,55,101],"distributed":[25,103],"training,":[26],"existing":[27],"research":[28],"predominantly":[30],"focused":[31],"on":[32],"offline":[33],"scheduling":[34,57,99],"individual":[36],"or":[37],"batched":[38],"training":[39,71,105,143],"tasks.":[40],"However,":[41],"the":[42,69,97,141],"stochastic":[43],"arrival":[44],"such":[46],"tasks":[47,106],"in":[48,59,151],"edge":[49,61,153],"networks":[50],"poses":[51],"a":[52,90,108,115],"critical":[53],"challenge":[54],"efficiently":[56],"them":[58,85],"resource-constrained":[60,152],"clusters.":[62],"In":[63],"this":[64],"paper,":[65],"aiming":[66],"to":[67],"minimize":[68],"average":[70,142],"completion":[72,144],"time":[73,145],"across":[74],"all":[75],"tasks,":[76],"we":[77,95],"first":[78],"extract":[79],"operator":[81],"graphs":[82],"and":[83,113,131],"partition":[84],"coarse-grained":[87],"subgraphs":[88],"using":[89],"max-flow":[91],"mincut":[92],"algorithm.":[93],"Then,":[94],"formulate":[96],"online":[98],"problem":[100],"as":[107],"Markov":[109],"Decision":[110],"Process":[111],"(MDP)":[112],"propose":[114],"reinforcement":[116],"learning-based":[117],"(RL-based)":[118],"solution.":[119],"Extensive":[120],"experiments":[121],"comparing":[122],"our":[123,138],"method":[124],"with":[125,155],"three":[126],"conventional":[127],"baselines":[128],"(FIFO,":[129],"SJF,":[130],"Greedy)":[132],"under":[133],"diverse":[134],"configurations":[135],"show":[136],"that":[137],"approach":[139],"reduces":[140],"by":[146],"12.95%,":[147],"demonstrating":[148],"its":[149],"effectiveness":[150],"environments":[154],"dynamic":[156],"workloads.":[157]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-01-15T00:00:00"}