{"id":"https://openalex.org/W4412876932","doi":"https://doi.org/10.1145/3711896.3737275","title":"Aligning and Balancing ID and Multimodal Representations for Recommendation","display_name":"Aligning and Balancing ID and Multimodal Representations for Recommendation","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876932","doi":"https://doi.org/10.1145/3711896.3737275"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737275","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737275","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061378094","display_name":"Binrui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Binrui Wu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-9056-9543","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102951040","display_name":"Shisong Tang","orcid":"https://orcid.org/0000-0002-4550-3950"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shisong Tang","raw_affiliation_strings":["KuaiShou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4550-3950","affiliations":[{"raw_affiliation_string":"KuaiShou Technology, Beijing, China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048556378","display_name":"Fan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Li","raw_affiliation_strings":["KuaiShou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-7772-9523","affiliations":[{"raw_affiliation_string":"KuaiShou Technology, Beijing, China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101364458","display_name":"Bing Han","orcid":"https://orcid.org/0000-0003-2838-2824"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Han","raw_affiliation_strings":["KuaiShou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5044-6368","affiliations":[{"raw_affiliation_string":"KuaiShou Technology, Beijing, China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101615823","display_name":"Chang Meng","orcid":"https://orcid.org/0000-0002-2914-6527"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Meng","raw_affiliation_strings":["KuaiShou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2914-6527","affiliations":[{"raw_affiliation_string":"KuaiShou Technology, Beijing, China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033074326","display_name":"Jingyu Xiao","orcid":"https://orcid.org/0000-0002-2394-2995"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingyu Xiao","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2394-2995","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012051562","display_name":"Jiechao Gao","orcid":"https://orcid.org/0000-0003-0628-1416"},"institutions":[{"id":"https://openalex.org/I1743320","display_name":"Palo Alto University","ror":"https://ror.org/04f812k67","country_code":"US","type":"education","lineage":["https://openalex.org/I1743320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiechao Gao","raw_affiliation_strings":["Center for SDGC, Stanford University, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0628-1416","affiliations":[{"raw_affiliation_string":"Center for SDGC, Stanford University, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1743320"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5061378094"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.9051,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91951343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5029","last_page":"5038"},"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7407760620117188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35275423526763916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3479764461517334},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3441392481327057},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3384150564670563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407760620117188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35275423526763916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3479764461517334},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3441392481327057},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3384150564670563}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737275","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737275","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876932.pdf","grobid_xml":"https://content.openalex.org/works/W4412876932.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1994389483","https://openalex.org/W2027731328","https://openalex.org/W2042281163","https://openalex.org/W2054141820","https://openalex.org/W2069870183","https://openalex.org/W2096451472","https://openalex.org/W2158515176","https://openalex.org/W2295739661","https://openalex.org/W2338447355","https://openalex.org/W2341865734","https://openalex.org/W2512971201","https://openalex.org/W2605350416","https://openalex.org/W2723293840","https://openalex.org/W2741249238","https://openalex.org/W2742272831","https://openalex.org/W2767826403","https://openalex.org/W2898085636","https://openalex.org/W2946044191","https://openalex.org/W2950416834","https://openalex.org/W2963655167","https://openalex.org/W2964182926","https://openalex.org/W2970793364","https://openalex.org/W2982108874","https://openalex.org/W3093002391","https://openalex.org/W3101704389","https://openalex.org/W3104789011","https://openalex.org/W3153108722","https://openalex.org/W3155450594","https://openalex.org/W3156002164","https://openalex.org/W4224318508","https://openalex.org/W4284882462","https://openalex.org/W4309185982","https://openalex.org/W4322718576","https://openalex.org/W4323655724","https://openalex.org/W4384648324","https://openalex.org/W4385565675","https://openalex.org/W4385682046","https://openalex.org/W4399695571","https://openalex.org/W4403221552","https://openalex.org/W4403577865","https://openalex.org/W6600669965","https://openalex.org/W6601158483"],"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":{"Large-scale":[0],"recommendation":[1],"systems":[2],"mainly":[3],"rely":[4],"on":[5,187,194],"sparse":[6],"ID":[7,21,37,87,126,177],"features,":[8],"struggling":[9],"with":[10],"data":[11],"sparsity.":[12],"It's":[13],"important":[14],"to":[15,19,42,52,83,99,112,150],"use":[16],"multimodal":[17,35,49,66,89,103,116,128,179],"information":[18],"assist":[20],"learning":[22,91],"for":[23,92,118,146],"better":[24],"performance.":[25],"However,":[26],"there":[27],"exists":[28],"two":[29,75,142],"challenges:":[30],"(1)":[31],"distribution":[32],"discrepancy":[33],"between":[34,140,176],"and":[36,77,85,88,127,136,178,190,202],"makes":[38],"direct":[39],"integration":[40],"prone":[41],"user-item":[43],"mismatch;":[44],"(2)":[45],"slower":[46],"convergence":[47],"of":[48,65,125,144,204],"representations":[50,90,129,145],"compared":[51],"ID,":[53],"causing":[54],"optimization":[55,157,169],"imbalance":[56],"under":[57],"a":[58,79,101,114,161],"unified":[59,115],"objective,":[60],"which":[61,108],"limits":[62],"the":[63,74,123,132,138,141,147,156,168,173,200],"potential":[64],"representations.":[67,180],"In":[68],"this":[69],"paper,":[70],"we":[71,159,182],"comprehensively":[72],"investigate":[73],"problems":[76],"proposes":[78],"framework":[80],"named":[81],"AB-Rec":[82,121],"align":[84],"balance":[86],"recommendation.":[93],"We":[94],"design":[95],"three":[96],"alignment":[97],"tasks":[98],"fine-tune":[100],"pre-trained":[102],"large":[104],"language":[105],"model":[106],"(MLLM),":[107],"is":[109],"then":[110],"utilized":[111],"generate":[113],"representation":[117,152],"each":[119],"item.":[120],"aligns":[122],"distributions":[124],"by":[130,171],"minimizing":[131],"in-batch":[133],"Wasserstein":[134],"distance,":[135],"maximizes":[137],"distance":[139],"types":[143],"same":[148],"item":[149],"avoid":[151],"collapse.":[153],"To":[154],"solve":[155],"imbalance,":[158],"propose":[160],"gradient":[162],"modulation":[163],"method":[164],"that":[165],"adaptively":[166],"controls":[167],"process":[170],"monitoring":[172],"contribution":[174],"differences":[175],"Finally,":[181],"conduct":[183],"extensive":[184],"offline":[185],"experiments":[186],"four":[188],"datasets":[189],"an":[191,195],"A/B":[192],"test":[193],"online":[196],"video":[197],"platform,":[198],"demonstrating":[199],"effectiveness":[201],"scalability":[203],"our":[205],"proposed":[206],"method.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}