{"id":"https://openalex.org/W4407750010","doi":"https://doi.org/10.1145/3718099","title":"Enhancing Recommender Systems: Deep Modality Alignment with Large Multi-Modal Encoders","display_name":"Enhancing Recommender Systems: Deep Modality Alignment with Large Multi-Modal Encoders","publication_year":2025,"publication_date":"2025-02-19","ids":{"openalex":"https://openalex.org/W4407750010","doi":"https://doi.org/10.1145/3718099"},"language":"en","primary_location":{"id":"doi:10.1145/3718099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718099","pdf_url":null,"source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3718099","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000225198","display_name":"Zixuan Yi","orcid":"https://orcid.org/0000-0002-7752-8650"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zixuan Yi","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","University of Glasgow,  Glasgow, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-7752-8650","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow,  Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102631471","display_name":"Zijun Long","orcid":"https://orcid.org/0000-0002-2008-960X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zijun Long","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","University of Glasgow,  Glasgow United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-2008-960X","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow,  Glasgow United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["school of computing science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0003-4701-3223","affiliations":[{"raw_affiliation_string":"school of computing science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["school of computing science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0003-3143-279X","affiliations":[{"raw_affiliation_string":"school of computing science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057657785","display_name":"Richard McCreadie","orcid":"https://orcid.org/0000-0002-2751-2087"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard McCreadie","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","University of Glasgow,  Glasgow United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-2751-2087","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow,  Glasgow United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":4.2822,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.94631945,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"3","issue":"4","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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":0.9986000061035156,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.820115327835083},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7235456705093384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6589946746826172},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6295887231826782},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5653294324874878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4567168951034546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33948904275894165},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2634008228778839},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07049092650413513}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.820115327835083},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7235456705093384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589946746826172},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6295887231826782},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5653294324874878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4567168951034546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33948904275894165},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2634008228778839},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07049092650413513},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3718099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718099","pdf_url":null,"source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:346632","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/62611.html>,","pdf_url":"https://eprints.gla.ac.uk/346632/1/346632.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Articles"}],"best_oa_location":{"id":"doi:10.1145/3718099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718099","pdf_url":null,"source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1486317198","https://openalex.org/W1690919088","https://openalex.org/W2069870183","https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2774267535","https://openalex.org/W2963655167","https://openalex.org/W2964258748","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W2971196067","https://openalex.org/W2982108874","https://openalex.org/W3094605801","https://openalex.org/W3138516171","https://openalex.org/W3153325943","https://openalex.org/W3192113933","https://openalex.org/W3205778609","https://openalex.org/W4283397964","https://openalex.org/W4284687944","https://openalex.org/W4285288414","https://openalex.org/W4306316975","https://openalex.org/W4306317674","https://openalex.org/W4313156423","https://openalex.org/W4320342563","https://openalex.org/W4327644571","https://openalex.org/W4379929801","https://openalex.org/W4384648324","https://openalex.org/W4384655891","https://openalex.org/W4386071687","https://openalex.org/W4386081664","https://openalex.org/W4390873312","https://openalex.org/W4393074151","https://openalex.org/W4393159223","https://openalex.org/W4394007376","https://openalex.org/W4402404329","https://openalex.org/W4402704596","https://openalex.org/W4403220147","https://openalex.org/W4403221702"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4288390103","https://openalex.org/W4317039510","https://openalex.org/W627697492"],"abstract_inverted_index":{"In":[0,91],"recent":[1],"years,":[2],"the":[3,16,47,51,59,85,89,96,105,130,162,172,175,215,223,242,254,264,270,280],"rapid":[4],"growth":[5],"of":[6,18,99,108,132,159,164,174,178,244,256,289],"online":[7],"multimedia":[8],"services,":[9],"such":[10],"as":[11,169,171,222],"e-commerce":[12],"platforms,":[13],"has":[14],"necessitated":[15],"development":[17],"personalised":[19],"recommendation":[20,48,147,154,204,216,237],"approaches":[21,282],"that":[22,183,209,263],"can":[23],"encode":[24],"diverse":[25,36],"content":[26],"about":[27],"each":[28,257],"item.":[29],"Indeed,":[30],"modern":[31],"multi-modal":[32,53,101,111,136,186,203,246,277],"recommender":[33,54,112],"systems":[34,55],"exploit":[35],"features":[37,60],"obtained":[38],"from":[39,63],"raw":[40],"images":[41],"and":[42,70,142,166,191,231,285,291],"item":[43],"descriptions":[44],"to":[45,83,103],"enhance":[46,95],"performance.":[49,238],"However,":[50],"existing":[52,197,202],"primarily":[56],"depend":[57],"on":[58],"extracted":[61],"individually":[62],"different":[64,76],"media":[65],"through":[66,155],"pre-trained":[67,165,184,230],"modality-specific":[68,198],"encoders,":[69,168,278],"exhibit":[71],"only":[72],"shallow":[73,106],"alignments":[74],"between":[75,88],"modalities,":[77],"thereby":[78],"limiting":[79],"these":[80,179,211,275],"systems\u2019":[81],"ability":[82],"capture":[84],"underlying":[86],"relationships":[87],"modalities.":[90],"this":[92],"article,":[93],"we":[94,128,207,261],"deep":[97],"alignment":[98,107,251],"large":[100,135,185,245,276],"encoders":[102,115,137,187,199,212,233,247],"address":[104],"modalities":[109],"in":[110,121,248,287],"systems.":[113],"These":[114],"have":[116],"previously":[117],"demonstrated":[118],"state-of-the-art":[119,134],"effectiveness":[120,243,290],"ranking":[122],"items":[123],"across":[124,200],"various":[125],"domains.":[126],"Specifically,":[127],"investigate":[129],"use":[131,163],"three":[133],"\u2013":[138,145],"CLIP":[139],"(dual-stream),":[140],"VLMo":[141,284],"BEiT-3":[143],"(unified)":[144],"for":[146,153,274],"tasks.":[148],"We":[149,181,239],"explore":[150],"their":[151],"benefits":[152],"using":[156],"a":[157],"range":[158],"strategies,":[160],"including":[161],"fine-tuned":[167,232],"well":[170],"evaluation":[173],"end-to-end":[176,219],"training":[177,220],"encoders.":[180],"show":[182,208,262],"generate":[188],"more":[189],"aligned":[190],"effective":[192,225,272],"user/item":[193],"representations":[194],"compared":[195],"with":[196,218,234],"four":[201],"datasets.":[205],"Furthermore,":[206],"fine-tuning":[210],"further":[213],"improves":[214],"performance,":[217],"emerging":[221],"most":[224,271],"paradigm,":[226],"significantly":[227],"outperforming":[228,279],"both":[229],"an":[235],"improved":[236],"also":[240],"demonstrate":[241],"facilitating":[249],"modality":[250,258],"by":[252],"evaluating":[253],"contribution":[255],"separately.":[259],"Finally,":[260],"dual-stream":[265],"approach,":[266],"specifically":[267],"CLIP,":[268],"is":[269],"architecture":[273],"unified":[281],"(i.e.,":[283],"BEiT3)":[286],"terms":[288],"efficiency.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}