{"id":"https://openalex.org/W7158325713","doi":"https://doi.org/10.48550/arxiv.2604.25179","title":"Mitigating Shared-Private Branch Imbalance via Dual-Branch Rebalancing for Multimodal Sentiment Analysis","display_name":"Mitigating Shared-Private Branch Imbalance via Dual-Branch Rebalancing for Multimodal Sentiment Analysis","publication_year":2026,"publication_date":"2026-04-28","ids":{"openalex":"https://openalex.org/W7158325713","doi":"https://doi.org/10.48550/arxiv.2604.25179"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.25179","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25179","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.25179","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134861034","display_name":"Chunlei Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Chunlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126740745","display_name":"Jiabin Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jiabin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134838101","display_name":"Pengbin Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Pengbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126739184","display_name":"Zhenglin Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Zhenglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017525809","display_name":"Chengyin Hu","orcid":"https://orcid.org/0009-0006-9589-0182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Chengyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134827611","display_name":"Zhongxue Gan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Zhongxue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123476931","display_name":"Chun Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Chun","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/T10667","display_name":"Emotion and Mood Recognition","score":0.7166000008583069,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7166000008583069,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.08910000324249268,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03060000017285347,"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/discriminative-model","display_name":"Discriminative model","score":0.7652000188827515},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.6062999963760376},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.3961000144481659},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.38420000672340393},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3734000027179718},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.3682999908924103},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3571000099182129},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.3337000012397766}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7652000188827515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626000046730042},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3734000027179718},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C171018156","wikidata":"https://www.wikidata.org/wiki/Q7370306","display_name":"Rotation formalisms in three dimensions","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.25179","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25179","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.25179","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25179","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7134292125701904}],"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],"Sentiment":[1],"Analysis":[2],"(MSA)":[3],"requires":[4],"integrating":[5],"language,":[6],"acoustic,":[7],"and":[8,34,65,71,81,93,136,187],"visual":[9],"signals":[10],"without":[11],"sacrificing":[12],"modality-specific":[13,35,79,156],"sentiment":[14,100],"evidence.":[15],"Existing":[16],"methods":[17],"mainly":[18],"improve":[19],"either":[20],"shared-private":[21,46],"decomposition":[22],"or":[23],"cross-modal":[24,161],"interaction.":[25],"Although":[26],"effective,":[27],"both":[28],"ultimately":[29],"depend":[30],"on":[31,113,184],"how":[32],"shared":[33,56,61,76,92,123,142],"evidence":[36],"is":[37,96],"organized":[38],"before":[39],"prediction.":[40,181],"We":[41],"observe":[42],"that,":[43],"under":[44],"standard":[45,117],"pipelines,":[47],"modality":[48],"heterogeneity":[49],"often":[50],"induces":[51],"a":[52,87,116,125,176],"branch-imbalance":[53],"process:":[54],"dominant":[55],"patterns":[57,157],"accumulate":[58],"in":[59,175],"the":[60,89,108,122,145,171,194],"branch,":[62,124,147],"yielding":[63],"redundant":[64],"modality-biased":[66],"evidence,":[67],"while":[68,158],"repeated":[69],"interaction":[70],"rigid":[72],"alignment":[73],"gradually":[74],"leak":[75],"information":[77],"into":[78],"channels":[80],"weaken":[82],"discriminative":[83,155],"private":[84,94,146],"representations.":[85],"As":[86],"result,":[88],"complementarity":[90],"between":[91],"representations":[95],"reduced,":[97],"limiting":[98],"robust":[99],"reasoning.":[101],"To":[102],"address":[103],"this":[104],"issue,":[105],"we":[106],"propose":[107],"Dual-Branch":[109],"Rebalancing":[110,165],"Framework":[111],"(DBR)":[112],"top":[114],"of":[115,207],"multimodal":[118],"decoupling":[119],"stage.":[120],"In":[121,144],"Temporal-Structural":[126],"Factorization":[127],"(TSF)":[128],"module":[129,153,168],"disentangles":[130],"temporal":[131],"evolution":[132],"from":[133,204],"structural":[134],"dependencies":[135],"adaptively":[137],"integrates":[138],"them":[139],"to":[140],"reduce":[141],"redundancy.":[143],"an":[148],"Anchor-Guided":[149],"Private":[150],"Routing":[151],"(AGPR)":[152],"preserves":[154],"allowing":[159],"controlled":[160],"borrowing.":[162],"A":[163],"Bidirectional":[164],"Fusion":[166],"(BRF)":[167],"then":[169],"reunifies":[170],"two":[172],"regularized":[173],"branches":[174],"context-aware":[177],"manner":[178],"for":[179],"final":[180],"Extensive":[182],"experiments":[183],"CMU-MOSI,":[185],"CMU-MOSEI,":[186],"MIntRec":[188],"demonstrate":[189],"that":[190,200],"DBR":[191],"consistently":[192],"outperforms":[193],"compared":[195],"baselines.":[196],"Further":[197],"analyses":[198],"show":[199],"these":[201],"improvements":[202],"come":[203],"coordinated":[205],"mitigation":[206],"branch":[208],"imbalance.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-30T00:00:00"}