{"id":"https://openalex.org/W7131419367","doi":"https://doi.org/10.48550/arxiv.2602.19385","title":"Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition","display_name":"Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W7131419367","doi":"https://doi.org/10.48550/arxiv.2602.19385"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.19385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19385","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.19385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009474433","display_name":"Minxue Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tang, Minxue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126828713","display_name":"Yangyang Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yangyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126850205","display_name":"Aolin Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Aolin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005527065","display_name":"Maziyar Baran Pouyan","orcid":"https://orcid.org/0000-0003-4946-7659"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pouyan, Maziyar Baran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126677094","display_name":"Taha Belkhouja Yujia Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Belkhouja, Taha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127907212","display_name":"Yujia Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Yujia","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009474433"],"corresponding_institution_ids":[],"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":null,"last_page":null},"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":0.7861999869346619,"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":0.7861999869346619,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.041099999099969864,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03009999915957451,"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/embedding","display_name":"Embedding","score":0.7400000095367432},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5996999740600586},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5234000086784363},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5012000203132629},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46070000529289246},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3944999873638153},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.34529998898506165}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7400000095367432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368999719619751},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856999754905701},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5081999897956848},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2779280203","wikidata":"https://www.wikidata.org/wiki/Q17121211","display_name":"Small data","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.19385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19385","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.19385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19385","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Recognizing":[0],"implicit":[1,42],"visual":[2],"and":[3,31,55,129],"textual":[4],"patterns":[5],"is":[6,45],"essential":[7],"in":[8,40,134],"many":[9],"real-world":[10],"applications":[11],"of":[12,52,87,144,161],"modern":[13],"AI.":[14],"However,":[15],"tackling":[16],"long-tail":[17],"pattern":[18,72],"recognition":[19],"tasks":[20],"remains":[21],"challenging":[22],"for":[23,70,99],"current":[24],"pre-trained":[25,35],"foundation":[26],"models":[27,36,90],"such":[28],"as":[29],"LLMs":[30],"VLMs.":[32],"While":[33],"finetuning":[34],"can":[37],"improve":[38],"accuracy":[39,150],"recognizing":[41],"patterns,":[43],"it":[44],"usually":[46],"infeasible":[47],"due":[48],"to":[49,148],"a":[50,118],"lack":[51],"training":[53,101,153],"data":[54,107,159],"high":[56],"computational":[57,78],"overhead.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,103],"propose":[63],"ADAMAB,":[64,145],"an":[65,105],"efficient":[66],"embedding":[67,89],"calibration":[68],"framework":[69],"few-shot":[71,135],"recognition.":[73],"To":[74,95],"maximally":[75],"reduce":[76],"the":[77,97,112,126,141],"costs,":[79],"ADAMAB":[80,124],"trains":[81],"embedder-agnostic":[82],"light-weight":[83],"calibrators":[84],"on":[85,111],"top":[86],"fixed":[88],"without":[91],"accessing":[92],"their":[93],"parameters.":[94],"mitigate":[96],"need":[98],"large-scale":[100],"data,":[102],"introduce":[104],"adaptive":[106],"augmentation":[108],"strategy":[109],"based":[110],"Multi-Armed":[113],"Bandit":[114],"(MAB)":[115],"mechanism.":[116],"With":[117],"modified":[119],"upper":[120],"confidence":[121],"bound":[122],"algorithm,":[123],"diminishes":[125],"gradient":[127],"shifting":[128],"offers":[130],"theoretically":[131],"guaranteed":[132],"convergence":[133],"training.":[136],"Our":[137],"multi-modal":[138],"experiments":[139],"justify":[140],"superior":[142],"performance":[143],"with":[146,154],"up":[147],"40%":[149],"improvement":[151],"when":[152],"less":[155],"than":[156],"5":[157],"initial":[158],"samples":[160],"each":[162],"class.":[163]},"counts_by_year":[],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2026-02-26T00:00:00"}