{"id":"https://openalex.org/W4414539448","doi":"https://doi.org/10.1109/icc52391.2025.11160773","title":"Distributed Inference Optimization for Large Language Model in Edge-Cloud Collaborative Networks","display_name":"Distributed Inference Optimization for Large Language Model in Edge-Cloud Collaborative Networks","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414539448","doi":"https://doi.org/10.1109/icc52391.2025.11160773"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11160773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11160773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","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/A5043067884","display_name":"Zideng Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zideng Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051161496","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0003-1311-9097"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":["China Mobile Research Institute,Department of Basic Network Technology Research,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Department of Basic Network Technology Research,Beijing,China,100876","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438940","display_name":"Qin Li","orcid":"https://orcid.org/0009-0005-0279-3192"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Li","raw_affiliation_strings":["China Mobile Research Institute,Department of Basic Network Technology Research,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Department of Basic Network Technology Research,Beijing,China,100876","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055860243","display_name":"Yuhao Chai","orcid":"https://orcid.org/0000-0003-3546-0536"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Chai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389531","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0002-5200-3516"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642156","display_name":"Yong Zhang","orcid":"https://orcid.org/0000-0003-4997-698X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081117495","display_name":"Yinglei Teng","orcid":"https://orcid.org/0000-0002-7170-4764"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglei Teng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028821253","display_name":"Da Guo","orcid":"https://orcid.org/0000-0001-9564-2994"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5043067884"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35016287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6161","last_page":"6166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.8495000004768372,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.8495000004768372,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.7597000002861023,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.7558000087738037,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6614999771118164},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5782999992370605},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41029998660087585},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4101000130176544},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.40709999203681946},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.3736000061035156},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823199987411499},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6614999771118164},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3450999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11160773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11160773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3172857592","https://openalex.org/W3202577926","https://openalex.org/W4327521519","https://openalex.org/W4361029763","https://openalex.org/W4391164333","https://openalex.org/W4392745409","https://openalex.org/W4395069551","https://openalex.org/W4399282321","https://openalex.org/W4400277194"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,10,33,91,101,106,160],"progressive":[2],"evolution":[3],"of":[4,13,105],"large":[5,36],"language":[6],"models":[7],"(LLMs)":[8],"and":[9,59,84,94,118,127],"increasing":[11],"need":[12,34],"computing":[14,29,92],"for":[15,23,35,70,100],"<tex":[16],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[17],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{6":[18],"G}$</tex>,":[19],"it":[20],"becomes":[21],"crucial":[22],"multiple":[24],"network":[25,95],"nodes":[26],"with":[27],"limited":[28],"resources":[30],"to":[31,45,121,131,149],"share":[32],"model":[37,56,113],"inference.":[38],"Model":[39],"partition":[40],"methods":[41],"have":[42],"been":[43,147],"proposed":[44,77,161],"enable":[46],"computation-intensive":[47],"artificial":[48],"intelligence":[49],"(AI)":[50],"services":[51],"by":[52],"splitting":[53],"an":[54],"AI":[55],"across":[57,125],"multi-edge":[58],"cloud":[60,128],"nodes.":[61,129],"In":[62],"this":[63],"paper,":[64],"a":[65,111,138],"distributed":[66],"inference":[67,133,165],"optimization":[68],"framework":[69],"transformer":[71,107],"decoder-only":[72],"based":[73,89,144],"LLMs":[74,124],"(DIO-LLMs)":[75],"is":[76,87],"in":[78],"edge-cloud":[79],"collaborative":[80],"networks.":[81],"The":[82],"partitioning":[83,114],"offloading":[85],"strategy":[86],"determined":[88],"on":[90],"workload":[93],"status.":[96],"DIO-LLMs":[97],"specifically":[98],"accounts":[99],"parallel":[102],"execution":[103],"capabilities":[104],"architecture.":[108],"It":[109],"employs":[110],"two-phase":[112],"strategy,":[115],"comprising":[116],"inter-layer":[117],"intra-layer":[119],"partitions,":[120],"effectively":[122,168],"distribute":[123],"edge":[126],"Additionally,":[130],"mitigate":[132],"latency":[134,166],"under":[135,157],"resource":[136],"limitations,":[137],"Greedy":[139],"Proximal":[140],"Policy":[141],"Optimization":[142],"(GPPO)":[143],"algorithm":[145,162],"has":[146],"developed":[148],"devise":[150],"optimal":[151],"strategies.":[152],"Simulation":[153],"results":[154],"indicate":[155],"that":[156],"memory":[158],"constraints,":[159],"can":[163],"reduce":[164],"more":[167],"than":[169],"other":[170],"baseline":[171],"algorithms.":[172]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}