{"id":"https://openalex.org/W4403791575","doi":"https://doi.org/10.1145/3664647.3681498","title":"DiffMM: Multi-Modal Diffusion Model for Recommendation","display_name":"DiffMM: Multi-Modal Diffusion Model for Recommendation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791575","doi":"https://doi.org/10.1145/3664647.3681498"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5039641800","display_name":"Yangqin Jiang","orcid":"https://orcid.org/0009-0002-3936-1703"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yangqin Jiang","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0002-3936-1703","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019844880","display_name":"Lianghao Xia","orcid":"https://orcid.org/0000-0003-0725-2211"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lianghao Xia","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-0725-2211","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014213168","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-6653-3788"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-6653-3788","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006684031","display_name":"Da Luo","orcid":"https://orcid.org/0000-0003-1183-8354"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Luo","raw_affiliation_strings":["Wechat, Tencent, Guang Zhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1183-8354","affiliations":[{"raw_affiliation_string":"Wechat, Tencent, Guang Zhou, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034893981","display_name":"Kangyi Lin","orcid":"https://orcid.org/0000-0001-6259-392X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangyi Lin","raw_affiliation_strings":["Wechat, Tencent, Guang Zhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6259-392X","affiliations":[{"raw_affiliation_string":"Wechat, Tencent, Guang Zhou, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091518548","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-2062-1512"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2062-1512","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7591","last_page":"7599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9876999855041504,"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/T11309","display_name":"Music and Audio Processing","score":0.9416999816894531,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6998881697654724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6618826985359192},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5662031173706055},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08309951424598694},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07459756731987}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6998881697654724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6618826985359192},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5662031173706055},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08309951424598694},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07459756731987},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/355877","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/355877","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"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":"Conference_Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2741249238","https://openalex.org/W2945827670","https://openalex.org/W2963085847","https://openalex.org/W2963655167","https://openalex.org/W2964258748","https://openalex.org/W2982108874","https://openalex.org/W3034876737","https://openalex.org/W3036167779","https://openalex.org/W3045200674","https://openalex.org/W3091746701","https://openalex.org/W3093002391","https://openalex.org/W3094605801","https://openalex.org/W3100278010","https://openalex.org/W3133849783","https://openalex.org/W3153325943","https://openalex.org/W3165959525","https://openalex.org/W3192113933","https://openalex.org/W3205778609","https://openalex.org/W3206310679","https://openalex.org/W4220909642","https://openalex.org/W4224316819","https://openalex.org/W4224983022","https://openalex.org/W4312933868","https://openalex.org/W4321593910","https://openalex.org/W4322718576","https://openalex.org/W4385567536","https://openalex.org/W4387846486","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,105],"rise":[1],"of":[2,33,151,157,176],"online":[3],"multi-modal":[4,82,97,128,159],"sharing":[5],"platforms":[6],"like":[7],"TikTok":[8],"and":[9,24,76],"YouTube":[10],"has":[11,49],"enabled":[12],"personalized":[13],"recommender":[14,56],"systems":[15,38],"to":[16,54,78,120,142],"incorporate":[17],"multiple":[18],"modalities":[19],"(such":[20],"as":[21],"visual,":[22],"textual,":[23],"acoustic)":[25],"into":[26],"user":[27,123],"representations.":[28],"However,":[29,58],"addressing":[30],"the":[31,81,155,174],"challenge":[32],"data":[34],"sparsity":[35],"in":[36,161],"these":[37,59],"remains":[39],"a":[40,95,109,115,145],"key":[41],"issue.":[42],"To":[43,88],"address":[44],"this":[45,90],"limitation,":[46],"recent":[47],"research":[48,91],"introduced":[50],"self-supervised":[51],"learning":[52,118],"techniques":[53],"enhance":[55],"systems.":[57],"methods":[60],"often":[61],"rely":[62],"on":[63,169],"simplistic":[64],"random":[65],"augmentation":[66],"or":[67],"intuitive":[68],"cross-view":[69],"information,":[70],"which":[71],"can":[72],"introduce":[73],"irrelevant":[74],"noise":[75],"fail":[77],"accurately":[79],"align":[80],"context":[83],"with":[84,114,131],"user-item":[85,146,163],"interaction":[86],"modeling.":[87,134],"fill":[89],"gap,":[92],"we":[93],"propose":[94],"novel":[96],"graph":[98,111,147],"diffusion":[99,112,138],"model":[100,113],"for":[101],"recommendation":[102],"called":[103],"DiffMM.":[104],"proposed":[106],"framework":[107],"integrates":[108],"modality-aware":[110,122],"cross-modal":[116],"contrastive":[117],"paradigm":[119],"improve":[121],"representation":[124],"learning,":[125],"better":[126],"aligning":[127],"feature":[129],"information":[130],"collaborative":[132],"relation":[133],"Our":[135],"approach":[136],"leverages":[137],"models'":[139],"generative":[140],"capabilities":[141],"automatically":[143],"generate":[144],"that":[148],"is":[149],"aware":[150],"different":[152],"modalities,":[153],"enabling":[154],"incorporation":[156],"useful":[158],"knowledge":[160],"modeling":[162],"interactions.":[164],"We":[165],"conduct":[166],"extensive":[167],"experiments":[168],"three":[170],"public":[171],"datasets,":[172],"demonstrating":[173],"superiority":[175],"our":[177],"DiffMM":[178],"over":[179],"various":[180],"competitive":[181],"baselines.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":47}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
