{"id":"https://openalex.org/W4403792040","doi":"https://doi.org/10.1145/3664647.3680933","title":"Exploring Stable Meta-Optimization Patterns via Differentiable Reinforcement Learning for Few-Shot Classification","display_name":"Exploring Stable Meta-Optimization Patterns via Differentiable Reinforcement Learning for Few-Shot Classification","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792040","doi":"https://doi.org/10.1145/3664647.3680933"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5103227773","display_name":"Zheng Han","orcid":"https://orcid.org/0000-0002-2584-5187"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Han","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078514263","display_name":"Xiaobin Zhu","orcid":"https://orcid.org/0000-0003-2702-4136"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Zhu","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015252816","display_name":"Chun Yang","orcid":"https://orcid.org/0000-0002-6297-4500"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yang","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040880250","display_name":"Hongyang Zhou","orcid":"https://orcid.org/0000-0002-4705-9304"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyang Zhou","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072850755","display_name":"Jingyan Qin","orcid":"https://orcid.org/0000-0002-4101-4316"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyan Qin","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Cheng Yin","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103227773"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6820425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1701","last_page":"1710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9954000115394592,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9954000115394592,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9933000206947327,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9890000224113464,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7223244905471802},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6968193054199219},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.6556715369224548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6393387913703918},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.612832248210907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5945671200752258},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.428210973739624},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4113367199897766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35176175832748413},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20636656880378723},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.18702968955039978},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10969969630241394},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07852596044540405}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7223244905471802},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6968193054199219},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6556715369224548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6393387913703918},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.612832248210907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5945671200752258},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.428210973739624},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4113367199897766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35176175832748413},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20636656880378723},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.18702968955039978},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10969969630241394},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07852596044540405},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2319453305","https://openalex.org/W2949879676","https://openalex.org/W2964137095","https://openalex.org/W2982247743","https://openalex.org/W2986604550","https://openalex.org/W2988501586","https://openalex.org/W3034587791","https://openalex.org/W3035143213","https://openalex.org/W3035531117","https://openalex.org/W3094724482","https://openalex.org/W3095891659","https://openalex.org/W3108878460","https://openalex.org/W3110214837","https://openalex.org/W3176276396","https://openalex.org/W3202188231","https://openalex.org/W3207175065","https://openalex.org/W3211144631","https://openalex.org/W4214562728","https://openalex.org/W4281250886","https://openalex.org/W4287121509","https://openalex.org/W4312800234","https://openalex.org/W4390873020","https://openalex.org/W4390874695","https://openalex.org/W4390938661","https://openalex.org/W4393154033","https://openalex.org/W4402716130","https://openalex.org/W6600339963"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W4294873804","https://openalex.org/W2806221744","https://openalex.org/W4383109125","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107"],"abstract_inverted_index":{"Existing":[0],"few-shot":[1,59,174],"learning":[2,13,31,71],"methods":[3,172],"generally":[4],"focus":[5],"on":[6],"designing":[7],"exquisite":[8],"structures":[9],"of":[10,21,30,87,163],"meta-learners":[11],"for":[12,58,74,114],"task-specific":[14],"prior":[15],"to":[16,38,63,93,105,126,138],"improve":[17,160],"the":[18,28,84,95,161],"discriminative":[19],"ability":[20],"global":[22],"embeddings.":[23,77],"However,":[24],"they":[25],"often":[26],"ignore":[27],"importance":[29],"stability":[32],"in":[33,68,91,173],"meta-training,":[34],"making":[35],"it":[36],"difficult":[37],"obtain":[39],"a":[40,102,133],"relatively":[41],"optimal":[42],"model.":[43],"From":[44],"this":[45],"key":[46],"observation,":[47],"we":[48,100,131],"propose":[49,101,132],"an":[50],"innovative":[51],"generic":[52],"differentiable":[53,80],"Reinforcement":[54],"Learning":[55],"(RL)":[56],"strategy":[57,82,121],"classification.":[60,175],"It":[61],"aims":[62],"explore":[64],"stable":[65],"meta-optimization":[66],"patterns":[67],"meta-training":[69],"by":[70],"generalizable":[72],"optimizations":[73],"producing":[75],"task-adaptive":[76],"Accordingly,":[78],"our":[79,119,157],"RL":[81],"models":[83],"embedding":[85],"procedure":[86],"feature":[88],"transformation":[89],"layers":[90],"meta-learner":[92],"optimize":[94],"gradient":[96],"flow":[97],"implicitly.":[98],"Also,":[99],"memory":[103],"module":[104],"associate":[106],"historical":[107],"and":[108,112,150,166],"current":[109],"task":[110,135,140],"states":[111],"actions":[113],"exploring":[115],"inter-task":[116],"similarity.":[117],"Notably,":[118],"RL-based":[120],"can":[122,159],"be":[123],"easily":[124],"extended":[125],"various":[127],"backbones.":[128],"In":[129],"addition,":[130],"novel":[134],"state":[136],"encoder":[137],"encode":[139],"representation,":[141],"which":[142],"fully":[143],"explores":[144],"inner-task":[145],"similarities":[146],"between":[147],"support":[148],"set":[149],"query":[151],"set.":[152],"Extensive":[153],"experiments":[154],"verify":[155],"that":[156],"approach":[158],"performance":[162],"different":[164],"backbones":[165],"achieve":[167],"promising":[168],"results":[169],"against":[170],"state-of-the-art":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}