{"id":"https://openalex.org/W4414360615","doi":"https://doi.org/10.24963/ijcai.2025/274","title":"Enhancing Multimodal Model Robustness Under Missing Modalities via Memory-Driven Prompt Learning","display_name":"Enhancing Multimodal Model Robustness Under Missing Modalities via Memory-Driven Prompt Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360615","doi":"https://doi.org/10.24963/ijcai.2025/274"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/274","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100981232","display_name":"Yihan Zhao","orcid":"https://orcid.org/0000-0002-8182-8437"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihan Zhao","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050052141","display_name":"Wei Xi","orcid":"https://orcid.org/0000-0001-9348-2982"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xi","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103805225","display_name":"Xiao Fu","orcid":"https://orcid.org/0009-0006-6601-5290"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Fu","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101471775","display_name":"Jizhong Zhao","orcid":"https://orcid.org/0000-0003-1037-9619"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhong Zhao","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"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":"2458","last_page":"2466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7926999926567078,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.7926999926567078,"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/T10320","display_name":"Neural Networks and Applications","score":0.7087000012397766,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.703000009059906,"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":0.7958999872207642},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.6717000007629395},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.644599974155426},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.616599977016449},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5320000052452087},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5248000025749207},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4287000000476837},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3781000077724457}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7958999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885000109672546},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6717000007629395},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.644599974155426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6184999942779541},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5636000037193298},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5320000052452087},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3781000077724457},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/274","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"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":{"Existing":[0],"multimodal":[1],"models":[2,29],"typically":[3],"assume":[4],"the":[5,37,134,137],"availability":[6],"of":[7,98,136],"all":[8],"modalities,":[9,60],"leading":[10],"to":[11,26,30,56,64,66,127,153,158,164],"significant":[12,141],"performance":[13,35,149],"degradation":[14],"when":[15,36],"certain":[16],"modalities":[17,86,126],"are":[18,40,93],"missing.":[19],"Recent":[20],"methods":[21,48],"have":[22],"introduced":[23],"prompt":[24,88,114],"learning":[25],"adapt":[27],"pretrained":[28],"incomplete":[31],"data,":[32],"achieving":[33,140],"remarkable":[34],"missing":[38,59,68,85],"cases":[39],"consistent":[41],"during":[42],"training":[43],"and":[44,54,102,162],"inference.":[45],"However,":[46],"these":[47],"rely":[49],"heavily":[50],"on":[51,155,160,166],"distribution":[52],"consistency":[53],"fail":[55],"compensate":[57],"for":[58,84],"limiting":[61],"their":[62],"ability":[63],"generalize":[65],"unseen":[67],"cases.":[69],"To":[70],"address":[71],"this":[72],"issue,":[73],"we":[74],"propose":[75],"Memory-Driven":[76],"Prompt":[77],"Learning,":[78],"a":[79,112],"framework":[80],"that":[81,116],"adaptively":[82],"compensates":[83],"through":[87],"learning.":[89],"The":[90,169],"compensation":[91],"strategies":[92],"achieved":[94],"by":[95],"two":[96],"types":[97],"prompts:":[99],"generative":[100],"prompts":[101,106,123],"shared":[103,122],"prompts.":[104],"Generative":[105],"retrieve":[107],"semantically":[108],"similar":[109],"samples":[110],"from":[111,151],"predefined":[113],"memory":[115],"stores":[117],"modality-specific":[118],"semantic":[119],"information,":[120],"while":[121],"leverage":[124],"available":[125,172],"provide":[128],"cross-modal":[129],"compensation.":[130],"Extensive":[131],"experiments":[132],"demonstrate":[133],"effectiveness":[135],"proposed":[138],"model,":[139],"improvements":[142],"across":[143],"diverse":[144],"missing-modality":[145],"scenarios,":[146],"with":[147],"average":[148],"increasing":[150],"34.76%":[152],"40.40%":[154],"MM-IMDb,":[156],"62.71%":[157],"77.06%":[159],"Food101,":[161],"60.40%":[163],"62.77%":[165],"Hateful":[167],"Memes.":[168],"code":[170],"is":[171],"at":[173],"https://github.com/zhao-yh20/MemPrompt.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}