{"id":"https://openalex.org/W7128605864","doi":"https://doi.org/10.48550/arxiv.2602.09445","title":"Personalized Parameter-Efficient Fine-Tuning of Foundation Models for Multimodal Recommendation","display_name":"Personalized Parameter-Efficient Fine-Tuning of Foundation Models for Multimodal Recommendation","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128605864","doi":"https://doi.org/10.48550/arxiv.2602.09445"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.09445","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123764177","display_name":"Sunwoo Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Sunwoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125674772","display_name":"Hyunjin Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Hyunjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125633703","display_name":"Kijung Shin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Kijung","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10453278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.8687999844551086,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.8687999844551086,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.02710000053048134,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.013799999840557575,"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/foundation","display_name":"Foundation (evidence)","score":0.7555000185966492},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6632999777793884},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5946999788284302},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5715000033378601},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5404000282287598},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.38920000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7555000185966492},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6632999777793884},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5404000282287598},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37610000371932983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32519999146461487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2624000012874603}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.09445","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.09445","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.09445","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:doi:10.48550/arxiv.2602.09445","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"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":{"In":[0],"recent":[1,34],"years,":[2],"substantial":[3],"research":[4],"has":[5],"integrated":[6],"multimodal":[7,17,50,88,147],"item":[8,47,55,74,112],"metadata":[9],"into":[10],"recommender":[11],"systems,":[12],"often":[13],"by":[14,94,162],"using":[15],"pre-trained":[16],"foundation":[18,51,148,195],"models":[19,26,52],"to":[20,72,102,108,146,164],"encode":[21],"such":[22],"data.":[23],"Since":[24],"these":[25],"are":[27,57],"not":[28,58],"originally":[29],"trained":[30],"for":[31,87],"recommendation":[32],"tasks,":[33],"works":[35],"efficiently":[36],"adapt":[37],"them":[38],"via":[39],"parameter-efficient":[40],"fine-tuning":[41],"(PEFT).":[42],"However,":[43],"even":[44,180],"with":[45,68,141,181],"PEFT,":[46],"embeddings":[48,56],"from":[49],"remain":[53],"user-blind:":[54],"conditioned":[59],"on":[60],"user":[61],"interests,":[62],"despite":[63],"the":[64,110,159,190,194],"fact":[65],"that":[66,117,128,155],"users":[67,93],"diverse":[69,173],"interests":[70],"attend":[71],"different":[73],"aspects.":[75],"To":[76],"address":[77],"this":[78,130],"limitation,":[79],"we":[80,153],"propose":[81],"PerPEFT,":[82],"a":[83,98,124],"personalized":[84],"PEFT":[85,100,143,174,183],"strategy":[86],"recommendation.":[89],"Specifically,":[90],"PerPEFT":[91,134,157],"groups":[92],"interest":[95],"and":[96,137,167,201],"assigns":[97],"distinct":[99],"module":[101,107],"each":[103,106],"group,":[104],"enabling":[105],"capture":[109],"fine-grained":[111],"aspects":[113],"most":[114],"predictive":[115],"of":[116,189,193],"group`s":[118],"purchase":[119],"decisions.":[120],"We":[121,197],"further":[122],"introduce":[123],"specialized":[125],"training":[126],"technique":[127],"strengthens":[129],"user-group":[131],"conditioning.":[132],"Notably,":[133],"is":[135,177],"PEFT-agnostic":[136],"can":[138],"be":[139],"paired":[140],"any":[142],"method":[144],"applicable":[145],"models.":[149],"Through":[150],"extensive":[151],"experiments,":[152],"show":[154],"(1)":[156],"outperforms":[158],"strongest":[160],"baseline":[161],"up":[163],"15.3%":[165],"(NDCG@20)":[166],"(2)":[168],"delivers":[169],"consistent":[170],"gains":[171],"across":[172],"variants.":[175],"It":[176],"noteworthy":[178],"that,":[179],"personalization,":[182],"remains":[184],"lightweight,":[185],"adding":[186],"only":[187],"1.3%":[188],"parameter":[191],"count":[192],"model.":[196],"provide":[198],"our":[199],"code":[200],"datasets":[202],"at":[203],"https://github.com/kswoo97/PerPEFT.":[204]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-02-12T00:00:00"}