{"id":"https://openalex.org/W4410294630","doi":"https://doi.org/10.26599/bdma.2025.9020031","title":"Training Large Models on Heterogeneous and Geo-Distributed Resource with Constricted Networks","display_name":"Training Large Models on Heterogeneous and Geo-Distributed Resource with Constricted Networks","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4410294630","doi":"https://doi.org/10.26599/bdma.2025.9020031"},"language":"en","primary_location":{"id":"doi:10.26599/bdma.2025.9020031","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2025.9020031","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/bdma.2025.9020031","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054041671","display_name":"Zan Zong","orcid":"https://orcid.org/0000-0002-7828-9030"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zan Zong","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Minkun Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minkun Guo","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032285247","display_name":"Mingshu Zhai","orcid":"https://orcid.org/0009-0009-7573-2250"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingshu Zhai","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033649899","display_name":"Yinan Tang","orcid":"https://orcid.org/0000-0002-6029-3744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinan Tang","raw_affiliation_strings":["IEIT SYSTEMS Co., Ltd.,Jinan,China,250014"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IEIT SYSTEMS Co., Ltd.,Jinan,China,250014","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024121684","display_name":"Jianjiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjiang Li","raw_affiliation_strings":["School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China,100083"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Communication Engineering, University of Science and Technology Beijing,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.136,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87273033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"8","issue":"4","first_page":"966","last_page":"980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.954200029373169,"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/T10320","display_name":"Neural Networks and Applications","score":0.9528999924659729,"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/computer-science","display_name":"Computer science","score":0.5715351700782776},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5306106209754944},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4472825229167938},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3912176489830017},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23856234550476074},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.15773066878318787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5715351700782776},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5306106209754944},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4472825229167938},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3912176489830017},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23856234550476074},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.15773066878318787},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/bdma.2025.9020031","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2025.9020031","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:776d3bf157a34d4885cc41f6b14eff79","is_oa":true,"landing_page_url":"https://doaj.org/article/776d3bf157a34d4885cc41f6b14eff79","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data Mining and Analytics, Vol 8, Iss 4, Pp 966-980 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/bdma.2025.9020031","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2025.9020031","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4242517151","display_name":null,"funder_award_id":"62225206","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G4536363530","display_name":null,"funder_award_id":"2022ZD0115304","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G647633398","display_name":null,"funder_award_id":"62402266","funder_id":"https://openalex.org/F4320331088","funder_display_name":"Natural Science Foundation for Young Scientists of Shanxi Province"}],"funders":[{"id":"https://openalex.org/F4320331088","display_name":"Natural Science Foundation for Young Scientists of Shanxi Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1982063824","https://openalex.org/W2897475915","https://openalex.org/W2969388332","https://openalex.org/W3012249773","https://openalex.org/W3043278179","https://openalex.org/W3132107458","https://openalex.org/W3142038251","https://openalex.org/W3168937343","https://openalex.org/W3206832494","https://openalex.org/W4283379731","https://openalex.org/W4309675765","https://openalex.org/W4364322902","https://openalex.org/W4383749415","https://openalex.org/W4385570483","https://openalex.org/W4386709668","https://openalex.org/W4395117922","https://openalex.org/W4402727885","https://openalex.org/W4409363181","https://openalex.org/W4410074278","https://openalex.org/W6727099177","https://openalex.org/W6746839373","https://openalex.org/W6751528251","https://openalex.org/W6756718674","https://openalex.org/W6763138067","https://openalex.org/W6769475105","https://openalex.org/W6778729859","https://openalex.org/W6799372109","https://openalex.org/W6801859478","https://openalex.org/W6811928498","https://openalex.org/W6838632916","https://openalex.org/W6838781100","https://openalex.org/W6848825725","https://openalex.org/W6850380837","https://openalex.org/W7046032890"],"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":{"As":[0],"the":[1,39,83,109,113,143,152,165,180,192,223,229],"computational":[2,28],"demands":[3],"driven":[4],"by":[5],"large":[6,132,206],"model":[7,133,166],"technologies":[8],"continue":[9],"to":[10,16,82,98,123,178,190],"grow":[11],"rapidly,":[12],"leveraging":[13],"GPU":[14,101],"hardware":[15,45,58,171],"expedite":[17],"parallel":[18,94,126],"training":[19,95,218],"processes":[20],"has":[21,46],"emerged":[22,47],"as":[23,48],"a":[24,31,49,67,174,184],"commonly-used":[25],"strategy.":[26],"When":[27],"resources":[29,64,76,102],"within":[30],"single":[32],"cluster":[33,226],"are":[34,77],"insufficient":[35],"for":[36,131,148,222],"large-model":[37],"training,":[38],"hybrid":[40],"utilization":[41,54],"of":[42,55,61,70,85,87,112,142,154,194],"heterogeneous":[43,56,88,115,125,139,149,170,201,225],"acceleration":[44,57],"promising":[50],"technical":[51],"solution.":[52],"The":[53,209],"and":[59,90,172],"scheduling":[60],"diverse":[62],"cloud":[63],"have":[65],"become":[66],"focal":[68],"point":[69],"considerable":[71],"interest.":[72],"However,":[73],"these":[74],"computing":[75,110],"often":[78],"geographically":[79],"distributed.":[80],"Due":[81],"lack":[84],"awareness":[86,153],"devices":[89],"network":[91],"topologies,":[92],"existing":[93],"frameworks":[96],"struggle":[97],"leverage":[99],"mixed":[100,224],"across":[103,128],"constrained":[104],"networks":[105],"effectively.":[106],"To":[107,159],"boost":[108],"capability":[111],"connected":[114,202],"clusters,":[116],"we":[117,163],"propose":[118],"HGTrainer,":[119],"an":[120],"optimizer":[121],"designed":[122],"plan":[124],"strategies":[127],"distributed":[129],"clusters":[130,140,203],"training.":[134],"HGTrainer":[135,199,214],"can":[136],"adaptively":[137],"saturate":[138],"because":[141],"expanded":[144],"tunable":[145],"parallelism":[146],"space":[147],"accelerators,":[150],"with":[151,204,228],"relatively":[155],"lower":[156],"inter-cluster":[157,195],"bandwidth.":[158],"achieve":[160],"this":[161],"goal,":[162],"formulate":[164],"partitioning":[167],"problem":[168],"among":[169],"introduce":[173],"hierarchical":[175],"searching":[176],"algorithm":[177],"solve":[179],"optimization":[181],"problem.":[182],"Besides,":[183],"mixed-precision":[185],"pipeline":[186],"method":[187],"is":[188],"used":[189],"reduce":[191],"cost":[193],"communications.":[196],"We":[197],"evaluate":[198],"on":[200,220],"popular":[205],"language":[207],"models.":[208],"experimental":[210],"result":[211],"shows":[212],"that":[213],"effectively":[215],"improves":[216],"1.49x":[217],"throughput":[219],"average":[221],"compared":[227],"state-of-the-art":[230],"Metis.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}