{"id":"https://openalex.org/W4415708235","doi":"https://doi.org/10.1109/icme59968.2025.11210066","title":"Social Optimum Assisted Gradient Modulation for Imbalanced Multimodal Learning","display_name":"Social Optimum Assisted Gradient Modulation for Imbalanced Multimodal Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708235","doi":"https://doi.org/10.1109/icme59968.2025.11210066"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5047334751","display_name":"Disen Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Disen Hu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786662","display_name":"Xun Jiang","orcid":"https://orcid.org/0000-0003-2209-651X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Jiang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025554387","display_name":"Zhe Sun","orcid":"https://orcid.org/0000-0002-6531-0769"},"institutions":[{"id":"https://openalex.org/I34077901","display_name":"Juntendo University","ror":"https://ror.org/01692sz90","country_code":"JP","type":"education","lineage":["https://openalex.org/I34077901"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhe Sun","raw_affiliation_strings":["Juntendo University,Japan"],"affiliations":[{"raw_affiliation_string":"Juntendo University,Japan","institution_ids":["https://openalex.org/I34077901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101662205","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0002-3599-9876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Meituan,China"],"affiliations":[{"raw_affiliation_string":"Meituan,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083536273","display_name":"Chong Peng","orcid":"https://orcid.org/0000-0002-6070-3600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Peng","raw_affiliation_strings":["Meituan,China"],"affiliations":[{"raw_affiliation_string":"Meituan,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115601168","display_name":"Peng Yan","orcid":"https://orcid.org/0000-0002-6211-4543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Yan","raw_affiliation_strings":["Meituan,China"],"affiliations":[{"raw_affiliation_string":"Meituan,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047334751"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31029545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2168000042438507,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2168000042438507,"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/T10028","display_name":"Topic Modeling","score":0.12160000205039978,"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":0.08529999852180481,"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":0.7961000204086304},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6043000221252441},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4713999927043915},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4438999891281128},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.42649999260902405},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4205000102519989},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.40380001068115234}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7961000204086304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6973000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680999994277954},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5116000175476074},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.40380001068115234},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1955857676","https://openalex.org/W2030931454","https://openalex.org/W2157966961","https://openalex.org/W2194775991","https://openalex.org/W2964109005","https://openalex.org/W3019023591","https://openalex.org/W3035333188","https://openalex.org/W4312639100","https://openalex.org/W4386038408","https://openalex.org/W4386076642","https://openalex.org/W4387969779","https://openalex.org/W4390873518","https://openalex.org/W4391287688","https://openalex.org/W4402660166","https://openalex.org/W4402716394","https://openalex.org/W4403791468","https://openalex.org/W4403863334","https://openalex.org/W4405717837","https://openalex.org/W4413156369"],"related_works":[],"abstract_inverted_index":{"The":[0],"imbalanced":[1,81],"modality":[2],"problem":[3],"in":[4,115],"multimodal":[5,62,82,108,150],"learning":[6,34,51],"is":[7],"a":[8,89,134],"vicious":[9],"phenomenon":[10],"that":[11],"leads":[12],"to":[13,20,41,74,105,110,128,133],"the":[14,17,21,25,28,32,43,46,50,53,59,80,107,112,117,130],"sub-optimization":[15],"of":[16,52,119],"modalities":[18,26,120],"due":[19],"gradient":[22,44,63],"conflicts":[23],"among":[24],"and":[27,65,87,145],"model\u2019s":[29,131],"preference":[30,132],"for":[31],"easier":[33],"modalities.":[35],"Recent":[36],"studies":[37],"have":[38],"been":[39],"dedicated":[40],"modulating":[42],"from":[45],"uni-modal":[47],"perspective,":[48],"boosting":[49],"single":[54],"modality.":[55,136],"Nevertheless,":[56],"they":[57],"overlook":[58],"similarity":[60],"between":[61,71],"optimization":[64,83],"multi-objective":[66],"learning,":[67],"while":[68],"overemphasizing":[69],"competition":[70],"modalities\u2019":[72],"gradients":[73],"improve":[75],"optimization.":[76],"Therefore,":[77],"we":[78,101],"perceive":[79],"as":[84],"Multi-Objective":[85],"Optimization,":[86],"propose":[88],"novel":[90],"training":[91],"method:":[92],"Social":[93],"Optimum":[94,104],"Assisted":[95],"Gradient":[96],"Modulation":[97],"(SOA-GM).":[98],"In":[99],"detail,":[100],"implemented":[102],"social":[103],"guide":[106],"model":[109],"achieve":[111],"trade-off":[113],"state":[114],"which":[116],"collaborations":[118],"can":[121],"be":[122],"maximized.":[123],"We":[124],"also":[125],"proposed":[126],"envy":[127],"reduce":[129],"particular":[135],"Finally,":[137],"experiments":[138],"across":[139],"multiple":[140],"datasets":[141],"indicate":[142],"our":[143],"superior":[144],"extendable":[146],"method":[147],"performance":[148],"on":[149],"learning.":[151]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}