{"id":"https://openalex.org/W4404034470","doi":"https://doi.org/10.1145/3666025.3699355","title":"LiteMoE: Customizing On-device LLM Serving via Proxy Submodel Tuning","display_name":"LiteMoE: Customizing On-device LLM Serving via Proxy Submodel Tuning","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404034470","doi":"https://doi.org/10.1145/3666025.3699355"},"language":"en","primary_location":{"id":"doi:10.1145/3666025.3699355","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3666025.3699355","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3666025.3699355","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3666025.3699355","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007042960","display_name":"Yan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Zhuang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087120799","display_name":"Zhenzhe Zheng","orcid":"https://orcid.org/0000-0002-5094-5331"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhe Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059190563","display_name":"Fan Wu","orcid":"https://orcid.org/0000-0003-0965-9058"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100428808","display_name":"Guihai Chen","orcid":"https://orcid.org/0000-0002-6934-1685"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guihai Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007042960"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.7439,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91176108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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":0.9919000267982483,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9909999966621399,"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/proxy","display_name":"Proxy (statistics)","score":0.7168636322021484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5578119158744812},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.3316507637500763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07193496823310852}],"concepts":[{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.7168636322021484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5578119158744812},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3316507637500763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07193496823310852}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3666025.3699355","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3666025.3699355","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3666025.3699355","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3666025.3699355","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3666025.3699355","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3666025.3699355","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G20903679","display_name":null,"funder_award_id":"2322206","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4806219103","display_name":"RII Track-4: Superparamagnetic Iron Oxide Nanoparticles as Recoverable Microwave Susceptors for Pre-hydrolysis of Waste Activated Sludge prior to Anaerobic Digestion","funder_award_id":"2132018","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404034470.pdf","grobid_xml":"https://content.openalex.org/works/W4404034470.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W398859631","https://openalex.org/W2342411541","https://openalex.org/W2539033431","https://openalex.org/W2560674852","https://openalex.org/W2605800822","https://openalex.org/W2626914210","https://openalex.org/W2897268228","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W3129831491","https://openalex.org/W4285134706","https://openalex.org/W4322766882","https://openalex.org/W4387212306","https://openalex.org/W4387212784","https://openalex.org/W4387321091","https://openalex.org/W4388874804","https://openalex.org/W4399121418","https://openalex.org/W4399140776","https://openalex.org/W4402671950","https://openalex.org/W4402683990"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Considering":[0],"limited":[1,56],"on-device":[2,57],"resources,":[3],"current":[4],"practices":[5],"are":[6,31,168],"attempting":[7],"to":[8,24,33,53,90,127,170],"deploy":[9],"a":[10,22,80,106,129,140,145],"system-level":[11],"mixture-of-experts":[12],"(MoE)-based":[13],"foundation":[14,68,137,190],"LLM":[15,44,138],"shared":[16],"by":[17],"multiple":[18],"mobile":[19,26,29,88,157,166],"apps":[20,30,64,89,167],"on":[21,95,174],"device":[23],"support":[25],"intelligence.":[27],"However,":[28],"hard":[32],"customize":[34],"their":[35],"services":[36],"that":[37,63,86,163],"require":[38],"tuning":[39,84],"adapters":[40,94,173],"associated":[41],"with":[42,164,186],"the":[43,55,60,67,136,188],"using":[45,97],"private":[46],"in-app":[47],"data.":[48],"The":[49,100,160],"difficulty":[50],"arises":[51],"due":[52],"both":[54],"resources":[58],"and":[59,118,123,131,149,156,181],"restricted":[61],"control":[62],"have":[65],"over":[66,152],"LLM.":[69,191],"To":[70],"address":[71],"this":[72,75],"issue,":[73],"in":[74],"work,":[76],"we":[77,115],"propose":[78],"LiteMoE,":[79,165],"novel":[81],"proxy":[82,98,133],"submodel":[83,108,134],"framework":[85],"supports":[87],"efficiently":[91],"fine-tune":[92,171],"customized":[93,172],"devices":[96],"submodels.":[99],"key":[101],"technique":[102],"behind":[103],"LiteMoE":[104,148],"is":[105],"post-training":[107],"extraction":[109],"method,":[110],"whereby":[111],"without":[112],"additional":[113],"re-training,":[114],"can":[116],"identify":[117],"reserve":[119],"critical":[120],"experts,":[121,126],"match":[122],"merge":[124],"moderate":[125],"extract":[128],"lightweight":[130],"effective":[132],"from":[135],"for":[139],"certain":[141],"app.":[142],"We":[143],"implemented":[144],"prototype":[146],"of":[147],"evaluated":[150],"it":[151],"various":[153],"MoE-based":[154],"LLMs":[155],"computing":[158],"tasks.":[159],"results":[161],"show":[162],"able":[169],"resource-limited":[175],"devices,":[176],"achieving":[177],"12.7%":[178],"accuracy":[179],"improvement":[180],"6.6\u00d7":[182],"memory":[183],"reduction":[184],"compared":[185],"operating":[187],"original":[189]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}