{"id":"https://openalex.org/W7131818780","doi":"https://doi.org/10.1109/tbdata.2026.3668564","title":"Diffusion-Based Multi-Agent With Reinforcement Learning for Multimodal-Based Recommendation","display_name":"Diffusion-Based Multi-Agent With Reinforcement Learning for Multimodal-Based Recommendation","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7131818780","doi":"https://doi.org/10.1109/tbdata.2026.3668564"},"language":null,"primary_location":{"id":"doi:10.1109/tbdata.2026.3668564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2026.3668564","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},"type":"article","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/A5123587613","display_name":"Yijun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I21642278","display_name":"Ningxia University","ror":"https://ror.org/04j7b2v61","country_code":"CN","type":"education","lineage":["https://openalex.org/I21642278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Hu","raw_affiliation_strings":["School of Information Engineering, Ningxia University, Yinchuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Ningxia University, Yinchuan, China","institution_ids":["https://openalex.org/I21642278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127065661","display_name":"Rui Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Tang","raw_affiliation_strings":["School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-3112-4861","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458818","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-5248-935X"},"institutions":[{"id":"https://openalex.org/I21642278","display_name":"Ningxia University","ror":"https://ror.org/04j7b2v61","country_code":"CN","type":"education","lineage":["https://openalex.org/I21642278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["School of Information Engineering, Ningxia University, Yinchuan, China"],"raw_orcid":"https://orcid.org/0000-0003-0954-5405","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Ningxia University, Yinchuan, China","institution_ids":["https://openalex.org/I21642278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127086046","display_name":"Xian Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I21642278","display_name":"Ningxia University","ror":"https://ror.org/04j7b2v61","country_code":"CN","type":"education","lineage":["https://openalex.org/I21642278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Mo","raw_affiliation_strings":["School of Information Engineering, Ningxia University, Yinchuan, China"],"raw_orcid":"https://orcid.org/0000-0002-1249-9190","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Ningxia University, Yinchuan, China","institution_ids":["https://openalex.org/I21642278"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.16177027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"3","first_page":"1070","last_page":"1082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.7627999782562256,"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":0.7627999782562256,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.012299999594688416,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.010200000368058681,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7398999929428101},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6409000158309937},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5426999926567078},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46129998564720154},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3287999927997589},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.30070000886917114},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.2980000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.897599995136261},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7398999929428101},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458999872207642},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5426999926567078},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2026.3668564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2026.3668564","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8544646609","display_name":null,"funder_award_id":"62306157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8783486029","display_name":null,"funder_award_id":"2024AAC05011","funder_id":"https://openalex.org/F4320322877","funder_display_name":"Natural Science Foundation of Ningxia Province"},{"id":"https://openalex.org/G8938456724","display_name":null,"funder_award_id":"2025BEH04048","funder_id":"https://openalex.org/F4320334010","funder_display_name":"Key Research and Development Program of Ningxia"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322877","display_name":"Natural Science Foundation of Ningxia Province","ror":null},{"id":"https://openalex.org/F4320334010","display_name":"Key Research and Development Program of Ningxia","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal-based":[0],"recommendation":[1,140,160],"integrates":[2],"visual,":[3],"textual,":[4],"and":[5,112,148,213],"acoustic":[6],"modalities":[7],"of":[8,151],"items":[9],"to":[10,64,79,109,145,169],"comprehensively":[11],"capture":[12],"user":[13],"preferences,":[14],"thereby":[15,104,154],"playing":[16],"a":[17,30,53,94,120,133],"crucial":[18],"role":[19],"in":[20,195],"modern":[21],"multimedia":[22,185],"online":[23],"platforms.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,118,163],"propose":[29],"<underline":[31,36,41,44,55,58,95,100,121,126,129],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[32,37,42,45,56,59,61,96,98,101,122,124,127,130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</u>iffusion-based":[33,57],"Multi-agent":[34],"with":[35,76,90,159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</u>einforcement":[38],"Learning":[39],"for":[40],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</u>ultimodal-based":[43],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Rec</u>ommendation":[46],"(DRMRec).":[47],"Specifically,":[48],"our":[49],"DRMRec":[50,190],"first":[51],"leverages":[52,138],"hierarchical":[54],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</u>ulti-<underline":[60],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</u>gent":[62],"(DMA)":[63],"reconstruct":[65],"the":[66,84,202,211],"user-item":[67],"interaction":[68,110],"graph.":[69],"Subsequently,":[70],"these":[71],"reconstructed":[72],"graphs":[73],"are":[74],"fused":[75],"multimodal":[77,91],"information":[78,92,107],"form":[80],"contrastive":[81,167,170],"views.":[82],"During":[83],"reconstruction,":[85],"each":[86,152],"agent":[87],"is":[88,199],"injected":[89],"through":[93],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</u>ross-<underline":[97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</u>odal":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</u>ligner":[102],"(CMA),":[103],"bringing":[105],"cross-modal":[106,165,178],"closer":[108],"embeddings":[111],"facilitating":[113],"alignment":[114],"across":[115,205],"modalities.":[116],"Then,":[117],"introduce":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</u>etric-<underline":[123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</u>ware":[125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</u>iffusion":[128],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</u>einforcer":[131],"(MADR),":[132],"reinforcement":[134],"learning":[135,168],"framework":[136],"that":[137,189,201],"validation-set":[139],"metrics":[141,208],"as":[142],"reward":[143],"signals":[144],"enable":[146],"dynamic":[147],"individual":[149],"fine-tuning":[150],"agent,":[153],"actively":[155],"aligning":[156],"model":[157],"optimization":[158],"tasks.":[161],"Next,":[162],"apply":[164],"graph":[166],"views,":[171],"alleviating":[172],"data":[173],"sparsity":[174],"while":[175],"further":[176],"enhancing":[177],"alignment.":[179],"Extensive":[180],"experiments":[181],"on":[182,209],"three":[183,207],"real-world":[184],"platform":[186],"datasets":[187,215],"demonstrate":[188],"consistently":[191],"outperforms":[192],"state-of-the-art":[193],"approaches":[194],"multimodal-based":[196],"recommendation.":[197],"It":[198],"noteworthy":[200],"performance":[203],"improvements":[204],"all":[206],"both":[210],"TikTok":[212],"Sports":[214],"exceed":[216],"10%.":[217]},"counts_by_year":[],"updated_date":"2026-05-15T06:05:50.897203","created_date":"2026-02-28T00:00:00"}