{"id":"https://openalex.org/W7155532152","doi":"https://doi.org/10.1145/3809166","title":"Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities","display_name":"Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155532152","doi":"https://doi.org/10.1145/3809166"},"language":"en","primary_location":{"id":"doi:10.1145/3809166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3809166","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3809166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052435920","display_name":"Zhixiong Chen","orcid":"https://orcid.org/0000-0003-4183-8857"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhixiong Chen","raw_affiliation_strings":["Queen Mary University of London"],"raw_orcid":"https://orcid.org/0000-0003-4183-8857","affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114804304","display_name":"Bingjie Zhu","orcid":"https://orcid.org/0009-0003-6232-6057"},"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":false,"raw_author_name":"Bingjie Zhu","raw_affiliation_strings":["Xidian University"],"raw_orcid":"https://orcid.org/0009-0003-6232-6057","affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029002143","display_name":"Jiangzhou Wang","orcid":"https://orcid.org/0000-0003-0881-3594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangzhou Wang","raw_affiliation_strings":["Southeast University"],"raw_orcid":"https://orcid.org/0000-0003-0881-3594","affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007557286","display_name":"Hyundong Shin","orcid":"https://orcid.org/0000-0003-3364-8084"},"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyundong Shin","raw_affiliation_strings":["Kyung Hee University"],"raw_orcid":"https://orcid.org/0000-0003-3364-8084","affiliations":[{"raw_affiliation_string":"Kyung Hee University","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134335515","display_name":"Arumugam Nallanathan","orcid":"https://orcid.org/0000-0001-8337-5884"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arumugam Nallanathan","raw_affiliation_strings":["Queen Mary University of London"],"raw_orcid":"https://orcid.org/0000-0001-8337-5884","affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134502400","display_name":"Dusit (Tao) 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 (Tao) Niyato","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University"],"raw_orcid":"https://orcid.org/0000-0002-7442-7416","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48115085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"58","issue":"12","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.10760000348091125,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.10760000348091125,"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/T10028","display_name":"Topic Modeling","score":0.1023000031709671,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.05999999865889549,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8007000088691711},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6147000193595886},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3659000098705292},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.34529998898506165},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2752000093460083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586999773979187},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8007000088691711},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6147000193595886},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48420000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.34529998898506165},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3809166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3809166","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2604.22906","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.22906","pdf_url":"https://arxiv.org/pdf/2604.22906","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3809166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3809166","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2010202670","https://openalex.org/W2023535408","https://openalex.org/W2141682101","https://openalex.org/W2147657366","https://openalex.org/W2950077417","https://openalex.org/W2962969034","https://openalex.org/W2963434219","https://openalex.org/W3008591352","https://openalex.org/W3035038672","https://openalex.org/W3107232831","https://openalex.org/W3132804089","https://openalex.org/W3135497297","https://openalex.org/W3180338279","https://openalex.org/W4361857829","https://openalex.org/W4375928954","https://openalex.org/W4385572928","https://openalex.org/W4390660333","https://openalex.org/W4390828922","https://openalex.org/W4395106447","https://openalex.org/W4400447774","https://openalex.org/W4404562740","https://openalex.org/W4405430228","https://openalex.org/W4405717632","https://openalex.org/W4406137623","https://openalex.org/W4407881031","https://openalex.org/W4409262447","https://openalex.org/W4409494152","https://openalex.org/W4412412131","https://openalex.org/W4412536658","https://openalex.org/W4412915583","https://openalex.org/W4413640445"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,17],"models":[2],"(LLMs)":[3],"have":[4],"advanced":[5],"rapidly,":[6],"emerging":[7],"as":[8],"versatile":[9],"tools":[10],"across":[11],"fields":[12],"thanks":[13],"to":[14,34,47,82],"their":[15,35],"exceptional":[16],"understanding,":[18],"generation,":[19],"and":[20,38,51,64,66,69,75],"reasoning":[21],"capabilities.":[22],"However,":[23],"performing":[24],"LLM":[25,48],"inference":[26,50],"at":[27],"the":[28,44,84],"network":[29],"edge":[30,49,90],"remains":[31],"challenging":[32],"due":[33],"large":[36],"memory":[37],"compute":[39],"demands.":[40],"This":[41],"survey":[42,80],"outlines":[43],"challenges":[45],"specific":[46],"provides":[52],"a":[53],"comprehensive":[54],"overview":[55],"of":[56,86],"recent":[57],"progress,":[58],"covering":[59],"system":[60],"architectures,":[61],"model":[62],"optimization":[63],"deployment,":[65],"resource":[67],"management":[68],"scheduling.":[70],"By":[71],"synthesizing":[72],"state-of-the-art":[73],"techniques":[74],"mapping":[76],"future":[77],"directions,":[78],"this":[79],"aims":[81],"unlock":[83],"potential":[85],"LLMs":[87],"in":[88],"resource-constrained":[89],"environments.":[91]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-25T00:00:00"}