{"id":"https://openalex.org/W4415539051","doi":"https://doi.org/10.1145/3746027.3755591","title":"Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysis","display_name":"Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysis","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539051","doi":"https://doi.org/10.1145/3746027.3755591"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5019091193","display_name":"M. X. Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Miaosen Luo","raw_affiliation_strings":["School of Computer Science, South China Normal University, GuangZhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, GuangZhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030884785","display_name":"Yuncheng Jiang","orcid":"https://orcid.org/0000-0002-0402-5382"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuncheng Jiang","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010270301","display_name":"Sijie Mai","orcid":"https://orcid.org/0000-0001-9763-375X"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijie Mai","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019091193"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91574625,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1997","last_page":"2006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.998199999332428,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.998199999332428,"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":0.9919999837875366,"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":0.9850999712944031,"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/interpretability","display_name":"Interpretability","score":0.9404000043869019},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7067999839782715},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5386999845504761},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4009000062942505},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.39399999380111694},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3864000141620636},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3716999888420105},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9404000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670000195503235},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7067999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243000030517578},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5300999879837036},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8910877470","display_name":null,"funder_award_id":"24KJ01","funder_id":"https://openalex.org/F4320321758","funder_display_name":"South China Normal University"}],"funders":[{"id":"https://openalex.org/F4320321758","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2556418146","https://openalex.org/W2625068411","https://openalex.org/W2787581402","https://openalex.org/W2883409523","https://openalex.org/W2915602689","https://openalex.org/W2924126491","https://openalex.org/W2949391930","https://openalex.org/W3021941048","https://openalex.org/W3034266838","https://openalex.org/W3048195943","https://openalex.org/W3093051361","https://openalex.org/W3128412859","https://openalex.org/W3141688548","https://openalex.org/W3187467055","https://openalex.org/W3197875592","https://openalex.org/W4206095984","https://openalex.org/W4285149123","https://openalex.org/W4285185970","https://openalex.org/W4288725119","https://openalex.org/W4308222497","https://openalex.org/W4312639100","https://openalex.org/W4319335604","https://openalex.org/W4319878933","https://openalex.org/W4384207713","https://openalex.org/W4385570923","https://openalex.org/W4385648800","https://openalex.org/W4385782081","https://openalex.org/W4386913496","https://openalex.org/W4388074308","https://openalex.org/W4388270316","https://openalex.org/W4390745579","https://openalex.org/W4396668454","https://openalex.org/W4400090301","https://openalex.org/W4400748097","https://openalex.org/W4403063401","https://openalex.org/W4404555269","https://openalex.org/W4415302351"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,52],"Sentiment":[1],"Analysis":[2],"(MSA)":[3],"faces":[4],"two":[5],"critical":[6,143],"challenges:":[7],"the":[8,13,41,48,51,94,109,136,155],"lack":[9],"of":[10,16,43,50,68,77,139,164,174],"interpretability":[11,42,175],"in":[12,25],"decision":[14],"logic":[15],"multimodal":[17],"fusion":[18],"and":[19,91,103,112,122,167,176,190],"modality":[20,101,170],"imbalance":[21,102],"caused":[22],"by":[23,99,159],"disparities":[24],"inter-modal":[26],"information":[27],"density.":[28],"To":[29],"address":[30],"these":[31],"issues,":[32],"we":[33,107],"propose":[34],"KAN-MCP,":[35],"a":[36],"novel":[37],"framework":[38],"that":[39],"integrates":[40],"Kolmogorov-Arnold":[44],"Networks":[45],"(KAN)":[46],"with":[47,130],"robustness":[49,98,177],"Clean":[53],"Pareto":[54],"(MCPareto)":[55],"framework.":[56],"First,":[57],"KAN":[58,129,140],"leverages":[59],"its":[60],"univariate":[61],"function":[62],"decomposition":[63],"to":[64,134],"achieve":[65],"transparent":[66],"analysis":[67],"cross-modal":[69],"interactions.":[70],"This":[71,126,172],"structural":[72],"design":[73],"allows":[74],"direct":[75],"inspection":[76],"feature":[78,124],"transformations":[79],"without":[80],"relying":[81],"on":[82,183,208],"external":[83],"interpretation":[84],"tools,":[85],"thereby":[86],"ensuring":[87,161],"both":[88],"high":[89],"expressiveness":[90],"interpretability.":[92],"Second,":[93],"proposed":[95],"MCPareto":[96,147],"enhances":[97],"addressing":[100],"noise":[104],"interference.":[105],"Specifically,":[106],"introduce":[108],"Dimensionality":[110],"Reduction":[111],"Denoising":[113],"Modal":[114],"Information":[115],"Bottleneck":[116],"(DRD-MIB)":[117],"method,":[118],"which":[119],"jointly":[120],"denoises":[121],"reduces":[123],"dimensionality.":[125],"approach":[127],"provides":[128],"discriminative":[131],"low-dimensional":[132],"inputs":[133],"reduce":[135],"modeling":[137],"complexity":[138],"while":[141],"preserving":[142],"sentiment-related":[144],"information.":[145],"Furthermore,":[146],"dynamically":[148],"balances":[149],"gradient":[150],"contributions":[151],"across":[152],"modalities":[153],"using":[154],"purified":[156],"features":[157],"output":[158],"DRD-MIB,":[160],"lossless":[162],"transmission":[163],"auxiliary":[165],"signals":[166],"effectively":[168],"alleviating":[169],"imbalance.":[171],"synergy":[173],"not":[178],"only":[179],"achieves":[180],"superior":[181],"performance":[182],"benchmark":[184],"datasets":[185],"such":[186],"as":[187],"CMU-MOSI,":[188],"CMU-MOSEI,":[189],"CH-SIMS":[191],"v2":[192],"but":[193],"also":[194],"offers":[195],"an":[196],"intuitive":[197],"visualization":[198],"interface":[199],"through":[200],"KAN's":[201],"interpretable":[202],"architecture.":[203],"Our":[204],"code":[205],"is":[206],"released":[207],"https://github.com/LuoMSen/KAN-MCP.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}