{"id":"https://openalex.org/W4416251182","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227782","title":"Mooe: Optimal Expert Deployment Scheme in Low-Rank Adaptation architecture","display_name":"Mooe: Optimal Expert Deployment Scheme in Low-Rank Adaptation architecture","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251182","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227782"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5112250386","display_name":"Shuzhen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhen Sun","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026063666","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-8135-8124"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110658926","display_name":"Xindian Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xindian Ma","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100364229","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0003-2213-8601"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20319999754428864,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20319999754428864,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07919999957084656,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.06859999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6966999769210815},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6018999814987183},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5837000012397766},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4472000002861023},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4422999918460846},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.438400000333786},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.3961000144481659}],"concepts":[{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6966999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6603999733924866},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2093647425","https://openalex.org/W2150884987","https://openalex.org/W2946609015","https://openalex.org/W2996908057","https://openalex.org/W2998617917","https://openalex.org/W4285247752","https://openalex.org/W4386075505","https://openalex.org/W4386857660","https://openalex.org/W4400525231","https://openalex.org/W4401024254"],"related_works":[],"abstract_inverted_index":{"Parameter-Efficient":[0],"Fine-Tuning":[1],"(PEFT)":[2],"techniques":[3],"have":[4],"significantly":[5],"reduced":[6],"costs":[7],"for":[8,60],"applying":[9],"large":[10],"language":[11],"models":[12],"(LLMs)":[13],"on":[14,29,98],"downstream":[15],"tasks.":[16,31],"However,":[17],"traditional":[18],"PEFT":[19,121],"structures":[20],"exhibit":[21],"poor":[22],"results":[23],"when":[24],"fine-tuning":[25,134],"some":[26,118],"complex":[27],"LLMs":[28],"difficult":[30],"To":[32,53],"solve":[33],"this":[34],"problem,":[35],"we":[36,76],"combine":[37],"the":[38,56,61,65,113,130,148],"Mixture":[39],"of":[40,64,73,109,132,139,143],"Experts":[41],"(MoE)":[42],"strategy":[43],"with":[44,49,55,123,135],"PEFT,":[45],"and":[46,68,81,91,105,117,146],"propose":[47],"MoE-LoRA":[48],"optimal":[50],"structure":[51,116],"(Mooe).":[52],"cope":[54],"model\u2019s":[57],"different":[58,99],"needs":[59],"differentiation":[62],"degree":[63],"MoE":[66],"module":[67],"meet":[69],"each":[70],"expert\u2019s":[71],"requirement":[72],"expressive":[74],"power,":[75],"design":[77],"a":[78],"pluripotency-capacity":[79],"balancing":[80],"expert-sharing":[82],"scheme.":[83],"It":[84,127],"enables":[85],"Mooe":[86,111],"to":[87],"acquire":[88],"higher":[89],"accuracy":[90],"greater":[92],"efficiency.":[93],"We":[94],"tested":[95],"our":[96],"method":[97],"models,":[100],"such":[101],"as":[102],"Llama3,":[103],"Phi3,":[104],"OPT.":[106],"In":[107],"terms":[108],"results,":[110],"outperforms":[112],"classical":[114],"LoRA":[115],"other":[119],"advanced":[120],"methods":[122],"fewer":[124],"trainable":[125],"parameters.":[126],"also":[128],"exceeds":[129],"effect":[131],"full":[133],"less":[136],"than":[137],"1%":[138],"original":[140],"parameters,":[141],"one-third":[142],"VRAM":[144],"usage,":[145],"half":[147],"training":[149],"time.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}