{"id":"https://openalex.org/W7151782876","doi":"https://doi.org/10.48550/arxiv.2604.05462","title":"Hierarchical Contrastive Learning for Multimodal Data","display_name":"Hierarchical Contrastive Learning for Multimodal Data","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151782876","doi":"https://doi.org/10.48550/arxiv.2604.05462"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.05462","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05462","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.05462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021350493","display_name":"Huichao Li","orcid":"https://orcid.org/0000-0002-1732-0196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Huichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101322616","display_name":"Junhan Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Junhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004052573","display_name":"Doudou Zhou","orcid":"https://orcid.org/0000-0002-0830-2287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Doudou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.8223999738693237,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.8223999738693237,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0617000013589859,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.015699999406933784,"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/identifiability","display_name":"Identifiability","score":0.8291000127792358},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6366999745368958},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5246999859809875},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5184999704360962},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5012999773025513},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4016000032424927}],"concepts":[{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.8291000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6661999821662903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370999813079834},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6366999745368958},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44699999690055847},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C169345407","wikidata":"https://www.wikidata.org/wiki/Q8216221","display_name":"Uncorrelated","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3452000021934509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26930001378059387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.05462","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05462","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.05462","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05462","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.42989587783813477}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"representation":[1],"learning":[2],"is":[3,26],"commonly":[4],"built":[5],"on":[6],"a":[7,57,69,74,82,93],"shared-private":[8],"decomposition,":[9,106],"treating":[10],"latent":[11,94,98],"information":[12],"as":[13],"either":[14],"common":[15],"to":[16,21],"all":[17],"modalities":[18,89],"or":[19],"specific":[20],"one.":[22],"This":[23],"binary":[24],"view":[25],"often":[27],"inadequate:":[28],"many":[29],"factors":[30],"are":[31],"shared":[32],"by":[33],"only":[34,88],"subsets":[35],"of":[36,103,128,134],"modalities,":[37],"and":[38,47,65,81,114,118,131,147],"ignoring":[39],"such":[40],"partial":[41],"sharing":[42],"can":[43],"over-align":[44],"unrelated":[45],"signals":[46],"obscure":[48],"complementary":[49],"information.":[50],"We":[51],"propose":[52],"Hierarchical":[53],"Contrastive":[54],"Learning":[55],"(HCL),":[56],"framework":[58],"that":[59,86,90],"learns":[60],"globally":[61],"shared,":[62,64],"partially":[63],"modality-specific":[66],"representations":[67,146],"within":[68],"unified":[70],"model.":[71],"HCL":[72,142],"combines":[73],"hierarchical":[75,105,129],"latent-variable":[76],"formulation":[77],"with":[78],"structural":[79],"sparsity":[80],"structure-aware":[83],"contrastive":[84],"objective":[85],"aligns":[87],"genuinely":[91],"share":[92],"factor.":[95],"Under":[96],"uncorrelated":[97],"variables,":[99],"we":[100],"prove":[101],"identifiability":[102],"the":[104,111],"establish":[107],"recovery":[108,127],"guarantees":[109],"for":[110,121],"loading":[112],"matrices,":[113],"derive":[115],"parameter":[116],"estimation":[117],"excess-risk":[119],"bounds":[120],"downstream":[122],"prediction.":[123],"Simulations":[124],"show":[125],"accurate":[126],"structure":[130],"effective":[132],"selection":[133],"task-relevant":[135],"components.":[136],"On":[137],"multimodal":[138],"electronic":[139],"health":[140],"records,":[141],"yields":[143],"more":[144],"informative":[145],"consistently":[148],"improves":[149],"predictive":[150],"performance.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-09T00:00:00"}