{"id":"https://openalex.org/W7139125815","doi":"https://doi.org/10.1109/globecom59602.2025.11432306","title":"A Runtime- and Cost-Efficient Approach of Deploying Mixture-of-Experts in Edge Networks","display_name":"A Runtime- and Cost-Efficient Approach of Deploying Mixture-of-Experts in Edge Networks","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7139125815","doi":"https://doi.org/10.1109/globecom59602.2025.11432306"},"language":null,"primary_location":{"id":"doi:10.1109/globecom59602.2025.11432306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","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/A5033731448","display_name":"Yuhan Wu","orcid":"https://orcid.org/0000-0002-2292-0727"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqian Wu","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129981281","display_name":"Danyang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danyang Zheng","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103174120","display_name":"Jiaqi Ren","orcid":"https://orcid.org/0000-0002-1562-7135"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Ren","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130042313","display_name":"Huanlai Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanlai Xing","raw_affiliation_strings":["Southwest Jiaotong University,School of Computing and Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computing and Artificial Intelligence,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130189305","display_name":"Wenyi Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I64852412","display_name":"Sichuan University of Science and Engineering","ror":"https://ror.org/053fzma23","country_code":"CN","type":"education","lineage":["https://openalex.org/I64852412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyi Tang","raw_affiliation_strings":["Sichuan University,School of Cyber Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,School of Cyber Science and Engineering,China","institution_ids":["https://openalex.org/I64852412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121444726","display_name":"Xiaojun Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojun Cao","raw_affiliation_strings":["Georgia State University,Department of Computer Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4843","last_page":"4848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.478300005197525,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.478300005197525,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.20730000734329224,"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/T14347","display_name":"Big Data and Digital Economy","score":0.11050000041723251,"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/software-deployment","display_name":"Software deployment","score":0.8716999888420105},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5857999920845032},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.412200003862381},{"id":"https://openalex.org/keywords/centrality","display_name":"Centrality","score":0.40380001068115234},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.3671000003814697}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.8716999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7208999991416931},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.412200003862381},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.257099986076355},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom59602.2025.11432306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3204998121","https://openalex.org/W4385567093","https://openalex.org/W4389519294","https://openalex.org/W4389520806","https://openalex.org/W4396781832","https://openalex.org/W4403259386","https://openalex.org/W4403320241","https://openalex.org/W4404338265","https://openalex.org/W4412722064"],"related_works":[],"abstract_inverted_index":{"Cloud-based":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5],"gained":[6],"widespread":[7],"adoption":[8],"among":[9],"human":[10],"users.":[11],"However,":[12],"when":[13],"the":[14,51,86,102,117,132,142,167],"users":[15,59],"shift":[16],"to":[17,30,49,78,112,130,166],"Internet-enabled":[18],"machines,":[19],"centralized":[20],"LLM":[21,74],"systems":[22],"often":[23],"suffer":[24],"from":[25],"high":[26],"latency":[27],"and":[28,53,72,96,140,160],"fail":[29],"provide":[31],"timely":[32],"responses.":[33],"Deploying":[34],"LLMs":[35,92],"over":[36],"edge":[37,79,138],"networks":[38],"presents":[39],"a":[40,61,67,94,124],"promising":[41],"alternative,":[42],"yet":[43],"maintaining":[44],"an":[45],"up-to-date":[46],"knowledge":[47],"base":[48],"address":[50,85],"dynamic":[52],"time-sensitive":[54],"demands":[55],"of":[56,88,120,134,145],"diverse":[57],"machine":[58],"remains":[60],"significant":[62],"challenge.":[63],"Consequently,":[64],"there":[65],"is":[66],"pressing":[68],"need":[69],"for":[70],"fast":[71],"cost-efficient":[73,97],"deployment":[75,114,163],"strategies":[76],"tailored":[77],"environments.":[80],"In":[81],"this":[82],"work,":[83],"we":[84,122],"problem":[87],"deploying":[89],"mixture-of-experts":[90],"(MoE)":[91],"in":[93,106],"runtime-":[95],"manner.":[98],"We":[99],"formally":[100],"define":[101],"Expert":[103,146],"Model":[104],"Deployment":[105,148],"Edge":[107],"Networks":[108],"(EMD-EN)":[109],"problem,":[110],"aiming":[111],"minimize":[113],"costs.":[115],"Leveraging":[116],"inherent":[118],"modularity":[119],"MoE,":[121],"propose":[123],"novel":[125],"Neighbor-First":[126],"Centrality":[127],"(NFC)":[128],"metric":[129],"facilitate":[131],"placement":[133],"model":[135],"components":[136],"across":[137],"nodes":[139],"design":[141],"NFC-based":[143],"Mixture":[144],"layer":[147],"(NFC-MoED)":[149],"algorithm.":[150],"Our":[151],"results":[152],"show":[153],"that":[154],"NFC-MoED":[155],"substantially":[156],"improves":[157],"runtime":[158],"efficiency":[159],"maintains":[161],"near-optimal":[162],"costs":[164],"compared":[165],"brute-force":[168],"benchmark.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-20T00:00:00"}