{"id":"https://openalex.org/W7138339933","doi":"https://doi.org/10.1609/aaai.v40i34.40084","title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","display_name":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138339933","doi":"https://doi.org/10.1609/aaai.v40i34.40084"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i34.40084","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40084","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i34.40084","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129727868","display_name":"Yutong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yutong Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052955622","display_name":"Zimeng Wu","orcid":"https://orcid.org/0000-0002-7792-8291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zimeng Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129705630","display_name":"Shengcai Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengcai Liao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739313","display_name":"Shujiang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujiang Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129679506","display_name":"Jiaxin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxin Chen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129727868"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55270198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"34","first_page":"28537","last_page":"28545"},"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":0.809499979019165,"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":0.809499979019165,"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/T11448","display_name":"Face recognition and analysis","score":0.05959999933838844,"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":0.019899999722838402,"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/forgetting","display_name":"Forgetting","score":0.7269999980926514},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.578499972820282},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5540000200271606},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5396000146865845},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4982999861240387},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3862999975681305},{"id":"https://openalex.org/keywords/side-effect","display_name":"Side effect (computer science)","score":0.35089999437332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465999722480774},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7269999980926514},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C3454156","wikidata":"https://www.wikidata.org/wiki/Q1144241","display_name":"Side effect (computer science)","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.2646999955177307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i34.40084","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40084","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i34.40084","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40084","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"transfer":[1,36],"learning":[2,37,58],"(PETL)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,73],"pivotal":[8],"paradigm":[9],"for":[10],"adapting":[11],"pre-trained":[12],"foundation":[13],"models":[14],"to":[15,93,116,132,166],"downstream":[16],"tasks,":[17],"significantly":[18,64],"reducing":[19],"trainable":[20],"parameters":[21],"yet":[22],"suffering":[23],"from":[24,107,127,141],"substantial":[25],"memory":[26,54,105,124,175],"overhead":[27],"caused":[28],"by":[29,42,136],"gradient":[30,45],"backpropagation":[31],"during":[32],"fine-tuning.":[33],"While":[34],"memory-efficient":[35],"(METL)":[38],"circumvents":[39],"this":[40],"challenge":[41],"bypassing":[43],"backbone":[44],"computation":[46],"via":[47],"lightweight":[48],"small":[49],"side":[50,61,119],"networks,":[51,62],"its":[52],"stringent":[53],"constraint":[55],"severely":[56],"limits":[57],"capacity":[59],"of":[60],"thereby":[63],"compromising":[65],"performance.":[66,150],"To":[67],"address":[68],"these":[69],"limitations,":[70],"we":[71,82,109],"propose":[72,84],"novel":[74],"Mixed-Precision":[75],"Interactive":[76,112],"Side":[77,113],"Mixture-of-Experts":[78,114],"framework":[79],"(MP-ISMoE).":[80],"Specifically,":[81],"first":[83],"an":[85],"Gaussian":[86],"Noise":[87],"Perturbed":[88],"Iterative":[89],"Quantization":[90],"(GNP-IQ)":[91],"scheme":[92],"quantize":[94],"weights":[95],"into":[96],"lower-bits":[97],"while":[98,170],"effectively":[99],"decreasing":[100],"quantization":[101],"errors.":[102],"By":[103],"leveraging":[104],"conserved":[106],"GNP-IQ,":[108],"subsequently":[110],"employ":[111],"(ISMoE)":[115],"scale":[117],"up":[118],"networks":[120],"without":[121],"sacrificing":[122],"overall":[123],"efficiency.":[125,176],"Different":[126],"conventional":[128],"mixture-of-experts,":[129],"ISMoE":[130],"learns":[131],"select":[133],"optimal":[134],"experts":[135],"interacting":[137],"with":[138],"salient":[139],"features":[140],"frozen":[142],"backbones,":[143],"thus":[144],"suppressing":[145],"knowledge":[146],"forgetting":[147],"and":[148,156,174],"boosting":[149],"Extensive":[151],"experiments":[152],"across":[153],"diverse":[154],"vision-language":[155],"language-only":[157],"tasks":[158],"demonstrate":[159],"that":[160],"MP-ISMoE":[161],"remarkably":[162],"promotes":[163],"accuracy":[164],"compared":[165],"state-of-the-art":[167],"METL":[168],"approaches,":[169],"maintaining":[171],"comparable":[172],"parameter":[173]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}