{"id":"https://openalex.org/W4392158858","doi":"https://doi.org/10.1109/globecom54140.2023.10436771","title":"Joint Foundation Model Caching and Inference of Generative AI Services for Edge Intelligence","display_name":"Joint Foundation Model Caching and Inference of Generative AI Services for Edge Intelligence","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4392158858","doi":"https://doi.org/10.1109/globecom54140.2023.10436771"},"language":"en","primary_location":{"id":"doi:10.1109/globecom54140.2023.10436771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom54140.2023.10436771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 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/A5053209543","display_name":"Minrui Xu","orcid":"https://orcid.org/0000-0002-8203-8146"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minrui Xu","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091266202","display_name":"Dusit Niyato","orcid":"https://orcid.org/0000-0002-7442-7416"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dusit Niyato","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440579","display_name":"Hongliang Zhang","orcid":"https://orcid.org/0000-0003-3393-8612"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Zhang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062761975","display_name":"Jiawen Kang","orcid":"https://orcid.org/0000-0002-8218-3490"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Kang","raw_affiliation_strings":["Guangdong University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005327587","display_name":"Zehui Xiong","orcid":"https://orcid.org/0000-0002-4440-941X"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zehui Xiong","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080122431","display_name":"Shiwen Mao","orcid":"https://orcid.org/0000-0002-7052-0007"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiwen Mao","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063667378","display_name":"Zhu Han","orcid":"https://orcid.org/0000-0002-6606-5822"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Zhu Han","raw_affiliation_strings":["University of Houston","Kyung Hee University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3548","last_page":"3553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9991000294685364,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9991000294685364,"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/T11478","display_name":"Caching and Content Delivery","score":0.9940999746322632,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/joint","display_name":"Joint (building)","score":0.7733653783798218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766637921333313},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7404123544692993},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6416300535202026},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6254655718803406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5400593280792236},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5103011131286621},{"id":"https://openalex.org/keywords/applications-of-artificial-intelligence","display_name":"Applications of artificial intelligence","score":0.42597177624702454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37413352727890015},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11823436617851257}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7733653783798218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766637921333313},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7404123544692993},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6416300535202026},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6254655718803406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400593280792236},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5103011131286621},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.42597177624702454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37413352727890015},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11823436617851257},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom54140.2023.10436771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom54140.2023.10436771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2785138646","display_name":null,"funder_award_id":"CNS-2148382,CNS-2107216,CNS-2128368,CMMI-2222810,ECCS-2302469","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2950865323","https://openalex.org/W2988216516","https://openalex.org/W3088768990","https://openalex.org/W4285197124","https://openalex.org/W4312933868","https://openalex.org/W4360836968","https://openalex.org/W4366457968","https://openalex.org/W4383753323","https://openalex.org/W4385571886","https://openalex.org/W4387415166","https://openalex.org/W4404658388","https://openalex.org/W4404782964","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2380075625","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W3135486588"],"abstract_inverted_index":{"With":[0,23],"the":[1,35,100,118,126,136,145,160,187],"rapid":[2],"development":[3],"of":[4,37,60,65,67,120,130,138],"artificial":[5],"general":[6],"intelligence":[7,32],"(AGI),":[8],"various":[9],"multimedia":[10],"services":[11],"based":[12],"on":[13,159],"pretrained":[14],"foundation":[15,90],"models":[16],"(PFMs)":[17],"need":[18],"to":[19,39,98,143,169],"be":[20],"effectively":[21,199],"deployed.":[22],"edge":[24,31,41,50,174],"servers":[25,51,175],"that":[26,96,186],"have":[27],"cloud-level":[28],"computing":[29,72],"power,":[30],"can":[33,52,190],"extend":[34],"capabilities":[36],"AGI":[38],"mobile":[40],"networks.":[42],"However,":[43],"compared":[44,194],"with":[45,176,195],"cloud":[46],"data":[47],"centers,":[48],"resource-limited":[49],"only":[53],"cache":[54],"and":[55,69,74,93,106,113,147,154,179],"execute":[56],"a":[57,88,132,164],"small":[58],"number":[59],"PFMs,":[61,131],"which":[62],"typically":[63],"consist":[64],"billions":[66],"parameters":[68],"require":[70],"intensive":[71],"power":[73],"GPU":[75],"memory":[76],"during":[77,117],"inference.":[78],"To":[79],"address":[80],"this":[81,84],"challenge,":[82],"in":[83,151],"paper,":[85],"we":[86,162],"propose":[87,163],"joint":[89],"model":[91,144],"caching":[92,167],"inference":[94,103,180],"framework":[95],"aims":[97],"balance":[99],"tradeoff":[101],"among":[102],"latency,":[104],"accuracy,":[105],"resource":[107],"consumption":[108],"by":[109,198],"managing":[110],"cached":[111,171],"PFMs":[112,172],"user":[114],"requests":[115],"efficiently":[116],"provisioning":[119],"generative":[121],"AI":[122],"services.":[123],"Specifically,":[124],"considering":[125],"in-context":[127],"learning":[128],"ability":[129],"new":[133],"metric":[134],"named":[135],"Age":[137],"Context":[139],"(AoC),":[140],"is":[141],"proposed":[142,188],"freshness":[146],"relevance":[148],"between":[149],"examples":[150],"past":[152],"demonstrations":[153],"current":[155],"service":[156],"requests.":[157],"Based":[158],"AoC,":[161],"least":[165],"context":[166],"algorithm":[168,189],"manage":[170],"at":[173],"historical":[177],"prompts":[178],"results.":[181],"The":[182],"numerical":[183],"results":[184],"demonstrate":[185],"reduce":[191],"system":[192],"costs":[193],"existing":[196],"baselines":[197],"utilizing":[200],"contextual":[201],"information.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}