{"id":"https://openalex.org/W4415538933","doi":"https://doi.org/10.1145/3746027.3755198","title":"GMML:Gradient-Modulated Robustness for Imbalance-Aware Multimodal Learning","display_name":"GMML:Gradient-Modulated Robustness for Imbalance-Aware Multimodal Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538933","doi":"https://doi.org/10.1145/3746027.3755198"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755198","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/A5102982739","display_name":"Zikai Zhang","orcid":"https://orcid.org/0000-0002-0371-1268"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zikai Zhang","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320157","display_name":"Xu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032992516","display_name":"Ziyi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Li","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010019122","display_name":"Yidong Li","orcid":"https://orcid.org/0000-0003-2965-6196"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Li","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019990791","display_name":"Yuanzhouhan Cao","orcid":"https://orcid.org/0000-0002-2064-8336"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhouhan Cao","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102982739"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17070544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7922","last_page":"7930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.993399977684021,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.993399977684021,"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":0.9743000268936157,"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/robustness","display_name":"Robustness (evolution)","score":0.7454000115394592},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48190000653266907},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4203999936580658},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.3917999863624573},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.37070000171661377}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7454000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685699999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031999945640564},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755198","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2588822028","https://openalex.org/W2886641317","https://openalex.org/W3168463823","https://openalex.org/W3196591432","https://openalex.org/W4297499129","https://openalex.org/W4385573131","https://openalex.org/W4402660166","https://openalex.org/W4414379910"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"learning":[1],"integrates":[2],"diverse":[3],"modalities":[4],"to":[5,33,50,66],"enhance":[6],"robustness,":[7],"yet":[8],"real-world":[9],"scenarios":[10],"suffer":[11],"from":[12],"heterogeneous":[13],"imbalance":[14,39,115],"phenomena":[15],"(noise":[16],"interference,":[17],"modality":[18,88],"partial":[19],"missing,":[20],"intermodal":[21],"information":[22],"disparities),":[23],"degrading":[24],"performance":[25],"through":[26],"biased":[27],"feature":[28],"representations.":[29],"Existing":[30],"methods":[31],"fail":[32],"adaptively":[34,59],"modulate":[35],"models":[36],"under":[37,87],"dynamic":[38],"conditions.":[40],"We":[41],"propose":[42],"GMML,":[43],"a":[44,93],"framework":[45],"dynamically":[46],"balancing":[47],"multimodal":[48],"gradients":[49],"counteract":[51],"imbalance-induced":[52],"biases:":[53],"i)":[54],"An":[55],"imbalance-aware":[56],"gradient":[57],"modulation":[58],"identifies":[60],"contributions":[61],"with":[62,102],"smooth":[63],"weight":[64],"transitions":[65],"balance":[67],"conflicting":[68],"gradients;":[69],"ii)":[70],"A":[71],"parameter":[72,81],"constraint":[73],"method":[74],"enforces":[75],"\u21132-norm":[76],"constraints":[77],"on":[78,125],"encoders,":[79],"suppressing":[80],"oscillations":[82],"and":[83,121,127],"blocking":[84],"noisy":[85],"updates":[86],"missing/noise.":[89],"Theoretically,":[90],"GMML":[91],"achieves":[92],"larger":[94],"certified":[95],"radius":[96,104],"upper":[97],"bound":[98],"for":[99],"complex":[100],"imbalances,":[101],"convergence":[103],"analysis":[105],"providing":[106],"theoretical":[107],"guarantees.":[108],"Experiments":[109],"demonstrate":[110],"superior":[111],"robustness":[112],"against":[113],"three":[114],"types,":[116],"outperforming":[117],"state-of-the-art":[118],"by":[119],"3.3%":[120],"2.3%":[122],"in":[123],"accuracy":[124],"KS":[126],"UCF-101":[128],"benchmarks.":[129],"series":[130],"Code:":[131],"https://github.com/zhangzikai-security-ML/GMML.":[132]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}