{"id":"https://openalex.org/W4415013311","doi":"https://doi.org/10.1145/3746027.3755779","title":"Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation","display_name":"Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415013311","doi":"https://doi.org/10.1145/3746027.3755779"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755779","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108986757","display_name":"Shouxing Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shouxing Ma","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101296394","display_name":"Zeng YaWen","orcid":"https://orcid.org/0000-0003-1908-1157"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yawen Zeng","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066180101","display_name":"Shiqing Wu","orcid":"https://orcid.org/0000-0001-6785-1203"},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Shiqing Wu","raw_affiliation_strings":["Faculty of Data Science, City University of Macau, Macau SAR, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Data Science, City University of Macau, Macau SAR, China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112808718","display_name":"Guandong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086892","display_name":"Education University of Hong Kong","ror":"https://ror.org/000t0f062","country_code":"HK","type":"education","lineage":["https://openalex.org/I4210086892"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guandong Xu","raw_affiliation_strings":["The Education University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Education University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210086892"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108986757"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42418843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6316","last_page":"6324"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9973999857902527,"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/T10028","display_name":"Topic Modeling","score":0.9815999865531921,"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/graph","display_name":"Graph","score":0.5019999742507935},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43700000643730164},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.42179998755455017},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.38659998774528503},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.374099999666214},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36469998955726624},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.35920000076293945},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.3490999937057495},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3328000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7594000101089478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5932000279426575},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.42179998755455017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27320000529289246},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755779","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.13745","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13745","pdf_url":"https://arxiv.org/pdf/2508.13745","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755779","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"recommender":[1],"system":[2],"focuses":[3],"on":[4,197],"utilizing":[5],"rich":[6],"modal":[7],"information":[8,92,160],"(":[9,55],"i.e.,":[10,56],"images":[11],"and":[12,53,88,108,133,146,157,177,187,223],"textual":[13],"descriptions)":[14],"of":[15,34,90,99,101,115,204],"items":[16],"to":[17,61,80,206],"improve":[18],"recommendation":[19],"performance.":[20],"The":[21,97,194],"current":[22],"methods":[23,40,68],"have":[24],"achieved":[25],"remarkable":[26],"success":[27],"with":[28,182],"the":[29,63,102,120,183,202],"powerful":[30],"structure":[31],"modeling":[32],"capability":[33],"graph":[35,176,181,192],"neural":[36],"networks.":[37],"However,":[38],"these":[39],"are":[41,59],"often":[42],"hindered":[43],"by":[44,143,217],"sparse":[45],"data":[46,64],"in":[47,93,112,154,161,219],"real-world":[48,199],"scenarios.":[49],"Although":[50],"contrastive":[51,141],"learning":[52,132,142],"homography":[54],"homogeneous":[57,166],"graphs)":[58],"employed":[60],"address":[62,119],"sparsity":[65],"challenge,":[66],"existing":[67,184],"still":[69],"suffer":[70],"two":[71],"main":[72],"limitations:":[73],"1)":[74],"Simple":[75],"multi-modal":[76,140],"feature":[77],"contrasts":[78],"fail":[79],"produce":[81],"effective":[82],"representations,":[83],"causing":[84],"noisy":[85],"modal-shared":[86,155,222],"features":[87,156],"loss":[89],"valuable":[91],"modal-unique":[94,162,224],"features;":[95],"2)":[96],"lack":[98],"exploration":[100],"homograph":[103],"relations":[104,135],"between":[105,221],"user":[106,174,185],"interests":[107],"item":[109,179,188],"co-occurrence":[110,180,186],"results":[111],"incomplete":[113],"mining":[114],"user-item":[116],"interplay.":[117],"To":[118,164],"above":[121],"limitations,":[122],"we":[123,138,169],"propose":[124],"a":[125,171],"novel":[126],"framework":[127],"for":[128,191],"\\textbf{R}\\textbf{E}fining":[129],"multi-mod\\textbf{A}l":[130],"cont\\textbf{R}astive":[131],"ho\\textbf{M}ography":[134],"(\\textbf{REARM}).":[136],"Specifically,":[137],"complement":[139],"employing":[144],"meta-network":[145],"orthogonal":[147],"constraint":[148],"strategies,":[149],"which":[150],"filter":[151],"out":[152],"noise":[153],"retain":[158],"recommendation-relevant":[159],"features.":[163,225],"mine":[165],"relationships":[167],"effectively,":[168],"integrate":[170],"newly":[172],"constructed":[173],"interest":[175],"an":[178,214],"semantic":[189],"graphs":[190],"learning.":[193],"extensive":[195],"experiments":[196],"three":[198],"datasets":[200],"demonstrate":[201],"superiority":[203],"REARM":[205,218],"various":[207],"state-of-the-art":[208],"baselines.":[209],"Our":[210],"visualization":[211],"further":[212],"shows":[213],"improvement":[215],"made":[216],"distinguishing":[220],"Code":[226],"is":[227],"available":[228],"\\href{https://github.com/MrShouxingMa/REARM}{here}.":[229]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}