{"id":"https://openalex.org/W4406459136","doi":"https://doi.org/10.1109/bigdata62323.2024.10825823","title":"Communication-Efficient Distributed LLM Training with Adaptive Traffic Control","display_name":"Communication-Efficient Distributed LLM Training with Adaptive Traffic Control","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459136","doi":"https://doi.org/10.1109/bigdata62323.2024.10825823"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-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/A5047081492","display_name":"Haiyan Jin","orcid":"https://orcid.org/0000-0002-0026-3025"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoying Jin","raw_affiliation_strings":["Xidian University,School of Telecommunications Engineering,Xi’An,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Telecommunications Engineering,Xi’An,China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047081492"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":1.0798,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80675636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8685","last_page":"8687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9922000169754028,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9922000169754028,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9919999837875366,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9878000020980835,"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":0.7553186416625977},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7274041771888733},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5308445692062378},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.44519737362861633},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4273951053619385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24399569630622864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553186416625977},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7274041771888733},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5308445692062378},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.44519737362861633},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4273951053619385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24399569630622864},{"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/bigdata62323.2024.10825823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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":8,"referenced_works":["https://openalex.org/W2060393849","https://openalex.org/W3091097978","https://openalex.org/W3153854431","https://openalex.org/W3154219392","https://openalex.org/W4327911839","https://openalex.org/W6760703128","https://openalex.org/W6794216301","https://openalex.org/W7052937856"],"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],"emergence":[1],"of":[2,96,166,171],"large":[3,62],"language":[4],"models":[5],"(LLMs)":[6],"calls":[7],"for":[8,13],"efficient":[9],"distributed":[10,23,97],"training":[11,25,40,99],"approaches":[12],"machine":[14],"learning":[15],"models.":[16],"In":[17],"the":[18,55,61,67,75,79,94,122,125,128,133,137,140,143,147,151,159,164,168],"traditional":[19],"PS":[20,129],"(Parameter":[21],"Server)-based":[22],"LLM":[24,98],"architecture,":[26],"one":[27],"or":[28],"more":[29],"servers":[30,49],"send":[31,45],"model":[32,39,52,56],"parameters":[33],"to":[34,48,50,60,86,120,157],"multiple":[35],"workers,":[36,66],"who":[37],"perform":[38],"using":[41],"local":[42],"data":[43],"and":[44,100,127,139],"back":[46],"gradients":[47,63,76,156],"update":[51],"weights":[53],"until":[54],"converges.":[57],"However,":[58],"due":[59],"produced":[64],"by":[65,74],"server":[68],"faces":[69],"high":[70],"communication":[71,160],"pressure":[72],"caused":[73],"sent":[77],"from":[78,82],"network":[80,149],"(usually":[81],"a":[83,111],"switch).":[84],"Aiming":[85],"solve":[87],"this":[88,90],"issue,":[89],"paper":[91],"first":[92],"analyzes":[93],"challenges":[95,170],"summarizes":[101],"existing":[102],"solutions":[103],"proposed":[104],"in":[105],"recent":[106],"years.":[107],"Then,":[108],"we":[109],"propose":[110],"new":[112],"architecture":[113,165],"based":[114],"on":[115],"adaptive":[116],"traffic":[117,134,144],"control,":[118],"SwitchATC,":[119,167],"reduce":[121,158],"communications":[123],"between":[124,136],"switch":[126,138,152],"server.":[130,141],"SwitchATC":[131,173],"monitors":[132],"rate":[135,145],"If":[142],"exceeds":[146],"server\u2019s":[148],"bandwidth,":[150],"will":[153],"remove":[154],"sparse":[155],"cost.":[161],"After":[162],"introducing":[163],"technological":[169],"implementing":[172],"are":[174],"discussed.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}