{"id":"https://openalex.org/W4388748451","doi":"https://doi.org/10.48550/arxiv.2311.09179","title":"SiRA: Sparse Mixture of Low Rank Adaptation","display_name":"SiRA: Sparse Mixture of Low Rank Adaptation","publication_year":2023,"publication_date":"2023-11-15","ids":{"openalex":"https://openalex.org/W4388748451","doi":"https://doi.org/10.48550/arxiv.2311.09179"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.09179","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.09179","pdf_url":"https://arxiv.org/pdf/2311.09179","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.09179","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100535647","display_name":"Yun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082749951","display_name":"Nevan Wichers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wichers, Nevan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112977814","display_name":"Chu\u2010Cheng Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Chu-Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382963","display_name":"Xinyi Wang","orcid":"https://orcid.org/0000-0003-2658-8650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017041036","display_name":"Tianlong Chen","orcid":"https://orcid.org/0009-0009-1397-9266"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007723627","display_name":"Lei Shu","orcid":"https://orcid.org/0000-0002-6700-9347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600832","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1573-2912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113048517","display_name":"Canoee Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Canoee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061709723","display_name":"Liangchen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Liangchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078094295","display_name":"Jindong Chen","orcid":"https://orcid.org/0000-0002-3940-9968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jindong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041574770","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0003-2672-8406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9973999857902527,"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":0.9973999857902527,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9772999882698059,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9718000292778015,"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/computer-science","display_name":"Computer science","score":0.8106023669242859},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6041347980499268},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.568713366985321},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5518537163734436},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5138152241706848},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4946708381175995},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48477238416671753},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4743848145008087},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4583932161331177},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4354464113712311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41284799575805664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2667132019996643},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07979550957679749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106023669242859},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6041347980499268},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.568713366985321},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5518537163734436},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5138152241706848},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4946708381175995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48477238416671753},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4743848145008087},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4583932161331177},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4354464113712311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41284799575805664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2667132019996643},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07979550957679749},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.09179","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.09179","pdf_url":"https://arxiv.org/pdf/2311.09179","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2311.09179","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.09179","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.09179","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.09179","pdf_url":"https://arxiv.org/pdf/2311.09179","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388748451.pdf","grobid_xml":"https://content.openalex.org/works/W4388748451.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W2782041652","https://openalex.org/W2952088488","https://openalex.org/W2612657834","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W4225691210","https://openalex.org/W2481230473","https://openalex.org/W2792147139","https://openalex.org/W2514220927"],"abstract_inverted_index":{"Parameter":[0],"Efficient":[1],"Tuning":[2],"has":[3],"been":[4],"an":[5],"prominent":[6],"approach":[7],"to":[8,14,31,81,122],"adapt":[9,32],"the":[10,22,42,59,76,83,90,100,124],"Large":[11],"Language":[12],"Model":[13],"downstream":[15],"tasks.":[16],"Most":[17],"previous":[18],"works":[19],"considers":[20],"adding":[21],"dense":[23],"trainable":[24,49],"parameters,":[25],"where":[26],"all":[27],"parameters":[28,50],"are":[29],"used":[30],"certain":[33],"task.":[34],"We":[35,109],"found":[36],"this":[37,56],"less":[38],"effective":[39],"empirically":[40],"using":[41],"example":[43],"of":[44,61,70,79,85,103,119,140],"LoRA":[45,136],"that":[46],"introducing":[47],"more":[48],"does":[51],"not":[52],"help.":[53],"Motivated":[54],"by":[55],"we":[57,130],"investigate":[58],"importance":[60],"leveraging":[62],"\"sparse\"":[63],"computation":[64],"and":[65,113,137,147],"propose":[66,110],"SiRA:":[67],"sparse":[68],"mixture":[69,139],"low":[71],"rank":[72],"adaption.":[73],"SiRA":[74,132],"leverages":[75],"Sparse":[77],"Mixture":[78],"Expert(SMoE)":[80],"boost":[82],"performance":[84],"LoRA.":[86],"Specifically":[87],"it":[88],"enforces":[89],"top":[91,118],"$k$":[92],"experts":[93],"routing":[94],"with":[95],"a":[96,111],"capacity":[97],"limit":[98],"restricting":[99],"maximum":[101],"number":[102],"tokens":[104],"each":[105],"expert":[106,115,141],"can":[107],"process.":[108],"novel":[112],"simple":[114],"dropout":[116],"on":[117],"gating":[120],"network":[121],"reduce":[123],"over-fitting":[125],"issue.":[126],"Through":[127],"extensive":[128],"experiments,":[129],"verify":[131],"performs":[133],"better":[134],"than":[135],"other":[138],"approaches":[142],"across":[143],"different":[144],"single":[145],"tasks":[146],"multitask":[148],"settings.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}