{"id":"https://openalex.org/W4416017679","doi":"https://doi.org/10.1145/3746252.3761367","title":"Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion","display_name":"Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017679","doi":"https://doi.org/10.1145/3746252.3761367"},"language":"en","primary_location":{"id":"doi:10.1145/3746252.3761367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.14485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012930762","display_name":"Moyu Zhang","orcid":"https://orcid.org/0000-0002-9104-1881"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Moyu Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102214282","display_name":"Yongxiang Tang","orcid":"https://orcid.org/0000-0003-1614-2444"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiang Tang","raw_affiliation_strings":["Unaffiliated, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unaffiliated, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109465593","display_name":"Yujun Jin","orcid":"https://orcid.org/0009-0003-0498-5804"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Jin","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032933252","display_name":"Jinxin Hu","orcid":"https://orcid.org/0000-0002-7252-5207"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxin Hu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103325731","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-8345-3835"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012930762"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48331207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4128","last_page":"4138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.8457000255584717,"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":0.8457000255584717,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04529999941587448,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.014600000344216824,"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/representation","display_name":"Representation (politics)","score":0.605400025844574},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5849000215530396},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5719000101089478},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5703999996185303},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49790000915527344},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4747999906539917},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4544999897480011},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4189000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791700005531311},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.605400025844574},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5849000215530396},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5126000046730042},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37549999356269836},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C150140777","wikidata":"https://www.wikidata.org/wiki/Q960648","display_name":"Point of interest","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.14485","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.14485","pdf_url":"https://arxiv.org/pdf/2508.14485","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.14485","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.14485","pdf_url":"https://arxiv.org/pdf/2508.14485","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2475334473","https://openalex.org/W2512971201","https://openalex.org/W2604202871","https://openalex.org/W2604662567","https://openalex.org/W2605350416","https://openalex.org/W2723293840","https://openalex.org/W2788728386","https://openalex.org/W2793768763","https://openalex.org/W2803718882","https://openalex.org/W2898085636","https://openalex.org/W2914271732","https://openalex.org/W2945772520","https://openalex.org/W2948903560","https://openalex.org/W2963981376","https://openalex.org/W2982902390","https://openalex.org/W2987999026","https://openalex.org/W2994850640","https://openalex.org/W3034792929","https://openalex.org/W3035313290","https://openalex.org/W3080642298","https://openalex.org/W3093519337","https://openalex.org/W3093601757","https://openalex.org/W3096591391","https://openalex.org/W3164006073","https://openalex.org/W3206127589","https://openalex.org/W4220819549","https://openalex.org/W4224307215","https://openalex.org/W4226337336","https://openalex.org/W4284701627","https://openalex.org/W4290927925","https://openalex.org/W4290944002","https://openalex.org/W4313156423","https://openalex.org/W4395022722","https://openalex.org/W4400528558","https://openalex.org/W4400721967","https://openalex.org/W4403577824"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"recommendation":[1,52,60,65],"methods":[2,34,66],"model":[3,240],"a":[4,8,192,202,216,237],"user's":[5,22,197],"interest":[6,100,133,170,184,223],"in":[7],"target":[9,157],"item":[10,56,158],"by":[11,88,195],"correlating":[12],"its":[13],"embedding":[14],"with":[15],"the":[16,21,42,84,95,107,120,127,135,152,156,164,196,220,255],"embeddings":[17],"of":[18,45,98,130,168,207,257],"items":[19,162],"from":[20,41],"interaction":[23],"history,":[24],"thereby":[25,105],"capturing":[26],"implicit":[27],"collaborative":[28],"filtering":[29],"signals.":[30],"Consequently,":[31],"traditional":[32],"ID-based":[33],"often":[35],"encounter":[36],"data":[37],"sparsity":[38],"problems":[39],"stemming":[40],"sparse":[43],"nature":[44],"ID":[46],"features.":[47],"To":[48],"mitigate":[49],"this":[50,117],"issue,":[51],"models":[53],"incorporate":[54],"multimodal":[55,64,99,114,132,247],"information":[57,248],"to":[58,102,110,200,218,243],"enhance":[59],"accuracy.":[61],"However,":[62],"existing":[63],"typically":[67],"rely":[68],"on":[69,76],"early":[70],"fusion":[71,129],"approaches,":[72],"which":[73,125,150,180,214],"focus":[74],"primarily":[75],"combining":[77],"text":[78],"and":[79,159,189,204],"image":[80],"features,":[81],"while":[82],"neglecting":[83],"dynamic":[85,96],"context":[86],"provided":[87],"user":[89,113,131,169,222],"behavior":[90],"sequences.":[91],"This":[92],"oversight":[93],"precludes":[94],"adaptation":[97],"representations":[101,185,224],"behavioral":[103,136,198],"patterns,":[104],"hindering":[106],"model's":[108],"ability":[109],"effectively":[111],"capture":[112],"interests.":[115],"Therefore,":[116],"paper":[118],"proposes":[119],"Distribution-Guided":[121],"Multimodal-Interest":[122],"Auto-Encoder":[123],"(DMAE),":[124],"achieves":[126],"cross":[128],"at":[134],"level.":[137],"Specifically,":[138],"DMAE":[139],"comprises":[140],"three":[141],"key":[142],"components:":[143],"1)":[144],"Multimodal":[145,175],"Interest":[146,176],"Encoding":[147],"Unit":[148,178,212],"(MIEU),":[149],"encodes":[151],"similarity":[153,227,233],"scores":[154],"between":[155],"historically":[160],"clicked":[161],"as":[163,236,245,249],"corresponding":[165],"representation":[166,206],"vectors":[167],"across":[171],"different":[172],"modalities.":[173],"2)":[174],"Fusion":[177],"(MIFU),":[179],"dynamically":[181],"adapts":[182],"these":[183],"through":[186],"both":[187],"intra-":[188],"inter-modal":[190],"fusion,":[191],"process":[193],"contextualized":[194],"sequence":[199],"achieve":[201],"fine-grained":[203],"behavior-aware":[205],"interest.":[208],"3)":[209],"Interest-Distribution":[210],"Decoding":[211],"(IDDU),":[213],"employs":[215],"decoder":[217],"reconstruct":[219],"encoded":[221],"into":[225],"true":[226],"distributions":[228,234],"for":[229,239],"each":[230],"modality.":[231],"The":[232],"serve":[235],"guide":[238],"learning,":[241],"aiming":[242],"retain":[244],"much":[246],"possible.":[250],"Ultimately,":[251],"extensive":[252],"experiments":[253],"demonstrate":[254],"superiority":[256],"DMAE.":[258]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}