{"id":"https://openalex.org/W7105650309","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228348","title":"MILES: Modality-Informed Learning Rate Scheduler for Balancing Multimodal Learning","display_name":"MILES: Modality-Informed Learning Rate Scheduler for Balancing Multimodal Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105650309","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228348"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Alejandro Guerra-Manzanares","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alejandro Guerra-Manzanares","raw_affiliation_strings":["New York University Abu Dhabi,Division of Engineering,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi,Division of Engineering,Abu Dhabi,UAE","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Farah E. Shamout","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farah E. Shamout","raw_affiliation_strings":["New York University Abu Dhabi,Division of Engineering,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi,Division of Engineering,Abu Dhabi,UAE","institution_ids":[]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.35089999437332153,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.35089999437332153,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.156700000166893,"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":0.08910000324249268,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.6180999875068665},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6019999980926514},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5659999847412109},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.5175999999046326},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41359999775886536},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3946000039577484},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537999749183655},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.6180999875068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5356000065803528},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330069","display_name":"Tamkeen","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2047393253","https://openalex.org/W2159941522","https://openalex.org/W2194775991","https://openalex.org/W2584561145","https://openalex.org/W2619383789","https://openalex.org/W2736232392","https://openalex.org/W3007868361","https://openalex.org/W3035333188","https://openalex.org/W3094595351","https://openalex.org/W4236737363","https://openalex.org/W4285107355","https://openalex.org/W4312639100","https://openalex.org/W4376226279","https://openalex.org/W4399759139"],"related_works":[],"abstract_inverted_index":{"The":[0,106],"aim":[1],"of":[2,29,45,57,118,207],"multimodal":[3,30,58,82,104,125,133,143,183,209],"neural":[4],"networks":[5,31],"is":[6,32,109],"to":[7,13,16,21,66,101,114,151],"combine":[8],"diverse":[9],"data":[10],"sources,":[11],"referred":[12],"as":[14],"modalities,":[15],"achieve":[17],"enhanced":[18,129],"performance":[19,130,150,184],"compared":[20],"relying":[22],"on":[23,43,141,211],"a":[24,87],"single":[25],"modality.":[26],"However,":[27],"training":[28,81,100,113],"typically":[33],"hindered":[34],"by":[35,123],"modality":[36,122,175,187],"overfitting,":[37],"where":[38],"the":[39,46,55,74,92,116,124,205],"network":[40],"relies":[41],"excessively":[42],"one":[44],"available":[47],"modalities.":[48,200],"This":[49,179],"often":[50],"yields":[51],"sub-optimal":[52],"performance,":[53],"hindering":[54],"potential":[56],"learning":[59,107,119,210],"and":[60,134,147,166,185],"resulting":[61],"in":[62,86,94,131,170,181],"marginal":[63],"improvements":[64],"relative":[65],"unimodal":[67,135,196],"models.":[68],"In":[69],"this":[70],"work,":[71],"we":[72],"present":[73],"Modality-Informed":[75],"Learning":[76],"ratE":[77],"Scheduler":[78],"(MILES)":[79],"for":[80,128],"joint":[83,144],"fusion":[84,145,167],"models":[85],"balanced":[88],"manner.":[89],"MILES":[90,140,159],"leverages":[91],"differences":[93],"modality-wise":[95],"conditional":[96],"utilization":[97],"rates":[98],"during":[99,112,177],"effectively":[102,173],"balance":[103,115],"learning.":[105],"rate":[108],"dynamically":[110],"adjusted":[111],"speed":[117],"from":[120],"each":[121],"model,":[126],"aiming":[127],"both":[132],"predictions.":[136],"We":[137],"extensively":[138],"evaluate":[139],"four":[142],"tasks":[146,165],"compare":[148],"its":[149],"seven":[152],"state-of-the-art":[153],"baselines.":[154],"Our":[155],"results":[156,180],"show":[157],"that":[158],"outperforms":[160],"all":[161,164],"baselines":[162],"across":[163],"methods":[168],"considered":[169],"our":[171,202],"study,":[172],"balancing":[174,208],"usage":[176],"training.":[178],"improved":[182],"stronger":[186],"encoders,":[188],"which":[189],"can":[190],"be":[191],"leveraged":[192],"when":[193],"dealing":[194],"with":[195],"samples":[197],"or":[198],"absent":[199],"Overall,":[201],"work":[203],"highlights":[204],"impact":[206],"improving":[212],"model":[213],"performance.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}