{"id":"https://openalex.org/W7133301178","doi":"https://doi.org/10.1109/tkde.2026.3667005","title":"Training-Free Graph-Based Imputation of Missing Modalities in Multimodal Recommendation","display_name":"Training-Free Graph-Based Imputation of Missing Modalities in Multimodal Recommendation","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133301178","doi":"https://doi.org/10.1109/tkde.2026.3667005"},"language":null,"primary_location":{"id":"doi:10.1109/tkde.2026.3667005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3667005","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","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/A5128080264","display_name":"Daniele Malitesta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Daniele Malitesta","raw_affiliation_strings":["Université Paris-Saclay, CentraleSupélec, Inria, Gif-sur-Yvette, France"],"raw_orcid":"https://orcid.org/0000-0003-2228-0333","affiliations":[{"raw_affiliation_string":"Université Paris-Saclay, CentraleSupélec, Inria, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128042227","display_name":"Emanuele Rossi","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Rossi","raw_affiliation_strings":["Sapienza University of Rome, Department of Computer Science, Rome, Italy"],"raw_orcid":"https://orcid.org/0009-0008-5882-4519","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Department of Computer Science, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029434859","display_name":"Claudio Pomo","orcid":"https://orcid.org/0000-0001-5206-3909"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Pomo","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5206-3909","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128065493","display_name":"Tommaso Di Noia","orcid":null},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tommaso Di Noia","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0939-5462","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087251228","display_name":"Fragkiskos D. Malliaros","orcid":"https://orcid.org/0000-0002-8770-3969"},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fragkiskos D. Malliaros","raw_affiliation_strings":["Université Paris-Saclay, CentraleSupélec, Inria, Gif-sur-Yvette, France"],"raw_orcid":"https://orcid.org/0000-0002-8770-3969","affiliations":[{"raw_affiliation_string":"Université Paris-Saclay, CentraleSupélec, Inria, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I4210107720"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.17292602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"5","first_page":"3250","last_page":"3263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.48429998755455017,"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":0.48429998755455017,"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":0.0820000022649765,"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":0.041600000113248825,"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/missing-data","display_name":"Missing data","score":0.7390999794006348},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.715499997138977},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.4977000057697296},{"id":"https://openalex.org/keywords/rss","display_name":"RSS","score":0.47839999198913574},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4510999917984009},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4302999973297119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259000182151794},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7390999794006348},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.715499997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5273000001907349},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.4977000057697296},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2776156558","wikidata":"https://www.wikidata.org/wiki/Q4353746","display_name":"MovieLens","level":4,"score":0.2703000009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2026.3667005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3667005","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6373819097","display_name":"Innovative diagnostic and therapeutic approaches in potassium channel developmental and epileptic encephalopathies (K-DEEs) using 4P for medicine","funder_award_id":"ANR-23-RHUS-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"recommender":[1],"systems":[2],"(RSs)":[3],"represent":[4],"items":[5,37],"in":[6,18,60,68,80,96,199,214],"the":[7,31,43,50,55,69,102,108,122,136,141,146,178,211,222],"catalog":[8],"through":[9],"multimodal":[10,44,61,97,112,138,153,167,182,215],"data":[11],"(e.g.,":[12],"product":[13],"images":[14],"and":[15,41,169,183],"descriptions)":[16],"that,":[17],"some":[19],"cases,":[20],"might":[21],"be":[22,161],"noisy":[23],"or":[24],"(even":[25],"worse)":[26],"missing.":[27],"In":[28,84],"those":[29],"scenarios,":[30],"common":[32],"practice":[33],"is":[34],"to":[35,144],"drop":[36],"with":[38,77],"missing":[39,58,78,94,111,147,204],"modalities":[40,59,95,205],"train":[42],"RSs":[45],"on":[46,121,151,221],"a":[47,72,90,115],"subsample":[48],"of":[49,57,110,117],"original":[51],"dataset.":[52],"To":[53],"date,":[54],"problem":[56,91,109,116],"recommendation":[62,154],"has":[63],"still":[64,173],"received":[65],"limited":[66],"attention":[67],"literature,":[70],"lacking":[71],"precise":[73],"formalisation":[74,92],"as":[75,114],"done":[76],"information":[79,113],"traditional":[81,184,197],"machine":[82,200],"learning.":[83],"this":[85,127],"work,":[86],"we":[87,106,129,187,208],"first":[88,212],"provide":[89],"for":[93],"recommendation.":[98],"Second,":[99],"by":[100],"leveraging":[101],"user-item":[103],"graph":[104,118,143,224],"structure,":[105],"re-cast":[107],"features":[119,139],"interpolation":[120],"item-item":[123,142,223],"co-purchase":[124],"graph.":[125],"On":[126],"basis,":[128],"propose":[130],"four":[131],"training-free":[132],"approaches":[133],"that":[134,157,189],"propagate":[135],"available":[137],"throughout":[140],"impute":[145],"features.":[148],"Extensive":[149],"experiments":[150],"popular":[152],"datasets":[155],"demonstrate":[156],"our":[158,190,227],"solutions":[159],"can":[160,193,225],"seamlessly":[162],"plugged":[163],"into":[164],"any":[165],"existing":[166],"RS":[168],"benchmarking":[170],"framework":[171],"while":[172],"preserving":[174],"(or":[175],"even":[176],"widen)":[177],"performance":[179],"gap":[180],"between":[181],"RSs.":[185],"Moreover,":[186],"show":[188],"graph-based":[191,228],"techniques":[192],"perform":[194],"better":[195],"than":[196],"imputations":[198],"learning":[201],"under":[202],"different":[203],"settings.":[206],"Finally,":[207],"analyse":[209],"(for":[210],"time":[213],"RSs)":[216],"how":[217],"feature":[218],"homophily":[219],"calculated":[220],"influence":[226],"imputations.":[229]},"counts_by_year":[],"updated_date":"2026-04-11T06:13:24.991567","created_date":"2026-02-24T00:00:00"}