{"id":"https://openalex.org/W2903396356","doi":null,"title":"KDGAN: Knowledge Distillation with Generative Adversarial Networks","display_name":"KDGAN: Knowledge Distillation with Generative Adversarial Networks","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2903396356","mag":"2903396356"},"language":"en","primary_location":{"id":"mag:2903396356","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/7358-kdgan-knowledge-distillation-with-generative-adversarial-networks.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5100351306","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-2565-5831","observed_orcids":["https://orcid.org/0000-0003-2565-5831"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2565-5831","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422092","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-8132-6250","observed_orcids":["https://orcid.org/0000-0002-8132-6250","https://orcid.org/0000-0001-8258-3585"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-8132-6250","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101870254","display_name":"Yu Sun","orcid":"https://orcid.org/0000-0001-5721-8017","observed_orcids":["https://orcid.org/0000-0001-5721-8017"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yu Sun","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5721-8017","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022290876","display_name":"Jianzhong Qi","orcid":"https://orcid.org/0000-0001-6501-9050","observed_orcids":["https://orcid.org/0000-0001-6501-9050"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianzhong Qi","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6501-9050","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9357,"has_fulltext":false,"cited_by_count":146,"citation_normalized_percentile":{"value":0.98419564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"775","last_page":"786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7250999808311462,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7250999808311462,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.24719999730587006,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.010499999858438969,"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/knowledge-distillation","display_name":"knowledge distillation","score":1.0},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.9929999709129333},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"multi-label classification","score":0.9020000100135803},{"id":"https://openalex.org/keywords/lightweight-classifiers","display_name":"lightweight classifiers","score":0.796999990940094},{"id":"https://openalex.org/keywords/three-player-games","display_name":"three-player games","score":0.765999972820282},{"id":"https://openalex.org/keywords/teacher-student-learning","display_name":"teacher-student learning","score":0.6669999957084656},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.703000009059906},{"id":"https://openalex.org/keywords/concrete-distribution","display_name":"concrete distribution","score":0.7089999914169312},{"id":"https://openalex.org/keywords/resource-constrained-inference","display_name":"resource-constrained inference","score":0.7699999809265137}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9178866147994995},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.856398344039917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490974068641663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6466107964515686},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6008570790290833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5707332491874695},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5598886609077454},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.507768452167511},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4531361162662506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4001922905445099},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2903396356","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/7358-kdgan-knowledge-distillation-with-generative-adversarial-networks.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1526445072","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1933349210","https://openalex.org/W1983988843","https://openalex.org/W2056624866","https://openalex.org/W2064675550","https://openalex.org/W2067562626","https://openalex.org/W2087560337","https://openalex.org/W2099471712","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2114315281","https://openalex.org/W2134797427","https://openalex.org/W2141225381","https://openalex.org/W2153579005","https://openalex.org/W2173379916","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2294370754","https://openalex.org/W2296701362","https://openalex.org/W2335875860","https://openalex.org/W2432004435","https://openalex.org/W2514480375","https://openalex.org/W2521028896","https://openalex.org/W2536305071","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2554314924","https://openalex.org/W2581485081","https://openalex.org/W2593729559","https://openalex.org/W2596763562","https://openalex.org/W2602076750","https://openalex.org/W2619206542","https://openalex.org/W2625357353","https://openalex.org/W2746626573","https://openalex.org/W2766736793","https://openalex.org/W2787017828","https://openalex.org/W2962946266","https://openalex.org/W2963474063","https://openalex.org/W2964268978","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2973721503","https://openalex.org/W6884734599","https://openalex.org/W3162484382","https://openalex.org/W7133670748","https://openalex.org/W3200303927","https://openalex.org/W3211483557","https://openalex.org/W4379983235","https://openalex.org/W4226116471","https://openalex.org/W3213237301","https://openalex.org/W4316035834"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1,155,171],"(KD)":[2],"aims":[3],"to":[4,10,57,70,83,93,117,121,210],"train":[5,72],"a":[6,31,34,76,79,114,131,138,140,143,199],"lightweight":[7],"classifier":[8,27,46,74,92,146,176,194],"suitable":[9],"provide":[11],"accurate":[12],"inference":[13],"with":[14,198],"constrained":[15],"resources":[16],"in":[17,78,230],"multi-label":[18],"learning.":[19],"Instead":[20],"of":[21,44,102,137,228],"directly":[22],"consuming":[23],"feature-label":[24],"pairs,":[25],"the":[26,45,59,64,73,91,95,100,148,162,170,175,179,184,188,193,196,203,218,226],"is":[28,50,55,69],"trained":[29,47,160],"by":[30,192],"teacher,":[32,141],"i.e.,":[33],"high-capacity":[35],"model":[36],"whose":[37],"training":[38,234],"may":[39,107],"be":[40],"resource-hungry.":[41],"The":[42,145],"accuracy":[43,232],"this":[48,103],"way":[49],"usually":[51],"suboptimal":[52],"because":[53],"it":[54,106],"difficult":[56],"learn":[58,94,150,178],"true":[60,96,180],"data":[61,97,181],"distribution":[62,98,182,190],"from":[63,151],"teacher.":[65],"An":[66],"alternative":[67],"method":[68],"adversarially":[71,159],"against":[75,161],"discriminator":[77,163],"two-player":[80,115],"game":[81,116,133],"akin":[82],"generative":[84],"adversarial":[85,165,173],"networks":[86],"(GAN),":[87],"which":[88,215],"can":[89],"ensure":[90],"at":[99,183],"equilibrium":[101,119],"game.":[104],"However,":[105],"take":[108],"excessively":[109],"long":[110],"time":[111],"for":[112],"such":[113],"reach":[118],"due":[120],"high-variance":[122],"gradient":[123,213],"updates.":[124],"To":[125],"address":[126],"these":[127],"limitations,":[128],"we":[129,206],"propose":[130],"three-player":[132],"named":[134],"KDGAN":[135,229],"consisting":[136],"classifier,":[139],"and":[142,147,157,172,233],"discriminator.":[144],"teacher":[149],"each":[152],"other":[153],"via":[154,164],"losses":[156],"are":[158],"losses.":[166],"By":[167],"simultaneously":[168],"optimizing":[169],"losses,":[174],"will":[177],"equilibrium.":[185],"We":[186],"approximate":[187],"discrete":[189],"learned":[191],"(or":[195],"teacher)":[197],"concrete":[200,204],"distribution.":[201],"From":[202],"distribution,":[205],"generate":[207],"continuous":[208],"samples":[209],"obtain":[211],"low-variance":[212],"updates,":[214],"speed":[216],"up":[217],"training.":[219],"Extensive":[220],"experiments":[221],"using":[222],"real":[223],"datasets":[224],"confirm":[225],"superiority":[227],"both":[231],"speed.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-12-11T00:00:00"}