{"id":"https://openalex.org/W7135180007","doi":"https://doi.org/10.1109/ton.2026.3673659","title":"Towards Optimal Communication Scheduling With Automatic Configuration for Distributed DNN Training","display_name":"Towards Optimal Communication Scheduling With Automatic Configuration for Distributed DNN Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7135180007","doi":"https://doi.org/10.1109/ton.2026.3673659"},"language":"en","primary_location":{"id":"doi:10.1109/ton.2026.3673659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2026.3673659","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","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/A5084558508","display_name":"J. Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Jinbin Hu","raw_affiliation_strings":["Changsha University of Science and Technology., Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8216-9683","affiliations":[{"raw_affiliation_string":"Changsha University of Science and Technology., Changsha, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101840557","display_name":"Xiaobin Xu","orcid":"https://orcid.org/0000-0001-8930-7241"},"institutions":[{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinming Xu","raw_affiliation_strings":["Changsha University of Science and Technology., Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changsha University of Science and Technology., Changsha, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128977079","display_name":"Hao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-9883-2400","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016523647","display_name":"Yiqing Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiqing Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003788132","display_name":"Xiaolin Chen","orcid":"https://orcid.org/0000-0001-5910-0661"},"institutions":[{"id":"https://openalex.org/I4210089944","display_name":"Qiongtai Teachers College","ror":"https://ror.org/00e42ba10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210089944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Chen","raw_affiliation_strings":["Qiongtai Normal University., Haikou, China"],"raw_orcid":"https://orcid.org/0000-0001-5910-0661","affiliations":[{"raw_affiliation_string":"Qiongtai Normal University., Haikou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395349","display_name":"Yiming Zhang","orcid":"https://orcid.org/0000-0001-5933-3043"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin Wang","orcid":"https://orcid.org/0000-0001-5473-8738"},"institutions":[{"id":"https://openalex.org/I121296143","display_name":"Hunan University of Science and Technology","ror":"https://ror.org/02m9vrb24","country_code":"CN","type":"education","lineage":["https://openalex.org/I121296143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Hunan University of Science and Technology., Xiangtan, China"],"raw_orcid":"https://orcid.org/0000-0001-5473-8738","affiliations":[{"raw_affiliation_string":"Hunan University of Science and Technology., Xiangtan, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048189907","display_name":"K. L. Chen","orcid":"https://orcid.org/0000-0003-2587-6028"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2587-6028","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5084558508"],"corresponding_institution_ids":["https://openalex.org/I56934997","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52377362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"4219","last_page":"4232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.10109999775886536,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.10109999775886536,"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/T11932","display_name":"Wireless Body Area Networks","score":0.07739999890327454,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.05299999937415123,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6065999865531921},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5626999735832214},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34200000762939453},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.29840001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945000290870667},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5626999735832214},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4526999890804291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3472000062465668},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2720000147819519}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ton.2026.3673659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2026.3673659","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-170332","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-170332","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G210794108","display_name":null,"funder_award_id":"T41-603/20R","funder_id":"https://openalex.org/F4320316806","funder_display_name":"Olympus Hong Kong and China"},{"id":"https://openalex.org/G3468037009","display_name":null,"funder_award_id":"62473146","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4299781706","display_name":null,"funder_award_id":"2025JJ20070","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G5998922274","display_name":null,"funder_award_id":"2024JJ3017","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G6396608774","display_name":null,"funder_award_id":"62472050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316806","display_name":"Olympus Hong Kong and China","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"ByteScheduler":[0,40,114,180],"partitions":[1],"and":[2,26,37,65,99,139,165],"rearranges":[3],"tensor":[4],"transmissions":[5],"to":[6,32,45,168],"improve":[7],"the":[8,23,27,33,47,51,72,102,106,113,122,131,159,173,179],"communication":[9],"efficiency":[10],"of":[11,20,35],"distributed":[12],"Deep":[13],"Neural":[14],"Network":[15],"(DNN)":[16],"training.":[17,81],"The":[18],"configuration":[19,49,75,93,176],"hyper-parameters":[21,52,104,160],"(i.e.,":[22],"partition":[24],"size":[25],"credit":[28],"size)":[29],"is":[30],"critical":[31],"effectiveness":[34],"partitioning":[36],"rearrangement.":[38],"Currently":[39],"adopts":[41],"Bayesian":[42],"Optimization":[43],"(BO)":[44],"find":[46],"optimal":[48,103],"for":[50,78,142],"beforehand.":[53],"In":[54],"practice,":[55],"however,":[56],"various":[57,150],"runtime":[58,124],"factors":[59],"(such":[60],"as":[61,105,126],"worker":[62],"node":[63],"status":[64],"network":[66],"conditions)":[67],"change":[68],"over":[69],"time,":[70],"making":[71],"statically-determined":[73],"one-shot":[74],"result":[76],"suboptimal":[77],"real-world":[79],"DNN":[80,151],"To":[82],"address":[83],"this":[84,87],"problem,":[85],"in":[86],"paper":[88],"we":[89],"present":[90],"a":[91,117],"realtime":[92],"method":[94,177],"(called":[95],"AutoByte)":[96],"that":[97,154],"automatically":[98],"timely":[100],"searches":[101],"training":[107],"systems":[108],"dynamically":[109,129,157],"change.":[110],"AutoByte":[111,155],"extends":[112],"framework":[115],"with":[116,161],"meta":[118],"network,":[119],"which":[120],"takes":[121],"systems\u2019":[123],"statistics":[125],"its":[127],"input,":[128],"adjusts":[130],"triggering":[132],"threshold":[133],"based":[134],"on":[135,149,178],"system":[136],"environment":[137],"characteristics,":[138],"outputs":[140],"predictions":[141],"speedups":[143],"under":[144],"specific":[145],"configurations.":[146],"Evaluation":[147],"results":[148],"models":[152],"show":[153],"can":[156],"tune":[158],"low":[162],"resource":[163],"usage,":[164],"deliver":[166],"up":[167],"33.2%":[169],"higher":[170],"performance":[171],"than":[172],"best":[174],"static":[175],"framework.":[181]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2026-03-14T00:00:00"}