{"id":"https://openalex.org/W7138915379","doi":"https://doi.org/10.1109/tpami.2026.3675685","title":"Principled Multimodal Representation Learning","display_name":"Principled Multimodal Representation Learning","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7138915379","doi":"https://doi.org/10.1109/tpami.2026.3675685","pmid":"https://pubmed.ncbi.nlm.nih.gov/41855053"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3675685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3675685","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101438813","display_name":"Xiaohao Liu","orcid":"https://orcid.org/0000-0001-6037-8580"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaohao Liu","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6037-8580","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114803721","display_name":"Xiaobo Xia","orcid":"https://orcid.org/0000-0003-3615-0919"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaobo Xia","raw_affiliation_strings":["University of Science and Technology of China, and National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3615-0919","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, and National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104253487","display_name":"See-Kiong Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"See-Kiong Ng","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6565-7511","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129876832","display_name":"Tat-Seng Chua","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":12.1051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97609957,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"48","issue":"8","first_page":"9114","last_page":"9128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.1784999966621399,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.1784999966621399,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14669999480247498,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1307000070810318,"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/modalities","display_name":"Modalities","score":0.6291999816894531},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6072999835014343},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5444999933242798},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5336999893188477},{"id":"https://openalex.org/keywords/singular-value","display_name":"Singular value","score":0.5049999952316284},{"id":"https://openalex.org/keywords/matrix-representation","display_name":"Matrix representation","score":0.47850000858306885},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.40230000019073486},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643000245094299},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6291999816894531},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6072999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6039999723434448},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C109282560","wikidata":"https://www.wikidata.org/wiki/Q4166054","display_name":"Singular value","level":3,"score":0.5049999952316284},{"id":"https://openalex.org/C103275481","wikidata":"https://www.wikidata.org/wiki/Q6787889","display_name":"Matrix representation","level":3,"score":0.47850000858306885},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3675685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3675685","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41855053","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41855053","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"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":{"Multimodal":[0,81],"representation":[1,8,126,167],"learning":[2],"seeks":[3],"to":[4,15,113,128,148,178],"create":[5],"a":[6,30,85,99,114,132,138],"unified":[7],"space":[9],"by":[10,57],"integrating":[11],"diverse":[12,172],"data":[13],"modalities":[14,94,130],"improve":[16],"multimodal":[17],"understanding.":[18],"Traditional":[19],"methods":[20],"often":[21],"depend":[22],"on":[23,29,158],"pairwise":[24],"contrastive":[25,156],"learning,":[26],"which":[27],"relies":[28],"predefined":[31],"anchor":[32,59,96],"modality,":[33],"restricting":[34],"alignment":[35,45,91,111],"across":[36,171],"all":[37],"modalities.":[38],"Recent":[39],"advances":[40],"have":[41],"investigated":[42],"the":[43,66,73,106,120,125,150,159],"simultaneous":[44,90],"of":[46,68,92,124],"multiple":[47,93],"modalities,":[48],"yet":[49],"several":[50],"challenges":[51],"remain,":[52],"such":[53],"as":[54,146],"limitations":[55],"imposed":[56],"fixed":[58],"points":[60],"and":[61,165],"instability":[62],"arising":[63],"from":[64],"optimizing":[65],"product":[67],"singular":[69,122,144,152],"values.":[70],"To":[71],"address":[72],"challenges,":[74],"in":[75,98,105],"this":[76],"paper,":[77],"we":[78],"propose":[79,137],"Principled":[80],"Representation":[82],"Learning":[83],"(PMRL),":[84],"novel":[86],"framework":[87],"that":[88,109,142],"achieves":[89],"without":[95],"dependency":[97],"more":[100],"stable":[101],"manner.":[102],"Specifically,":[103],"grounded":[104],"theoretical":[107],"insight":[108],"full":[110],"corresponds":[112],"rank-1":[115],"Gram":[116],"matrix,":[117],"PMRL":[118],"optimizes":[119],"dominant":[121],"value":[123],"matrix":[127],"align":[129],"along":[131],"shared":[133],"leading":[134,160],"direction.":[135],"We":[136],"softmax-based":[139],"loss":[140],"function":[141],"treats":[143],"values":[145],"logits":[147],"prioritize":[149],"largest":[151],"value.":[153],"Besides,":[154],"instance-wise":[155],"regularization":[157],"eigenvectors":[161],"maintains":[162],"inter-instance":[163],"separability":[164],"prevents":[166],"collapse.":[168],"Extensive":[169],"experiments":[170],"tasks":[173],"demonstrate":[174],"PMRL's":[175],"superiority":[176],"compared":[177],"baseline":[179],"methods.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-07T06:14:10.401900","created_date":"2026-03-20T00:00:00"}