{"id":"https://openalex.org/W2903707108","doi":"https://doi.org/10.1609/aaai.v33i01.33015628","title":"Training Deep Neural Networks in Generations: A More Tolerant Teacher Educates Better Students","display_name":"Training Deep Neural Networks in Generations: A More Tolerant Teacher Educates Better Students","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2903707108","doi":"https://doi.org/10.1609/aaai.v33i01.33015628","mag":"2903707108"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33015628","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015628","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4506/4384","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4506/4384","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101879663","display_name":"Chenglin Yang","orcid":"https://orcid.org/0000-0002-0834-5164"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chenglin Yang","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075290241","display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingxi Xie","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067478162","display_name":"Siyuan Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Qiao","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan L. Yuille","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101879663"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":10.7785,"has_fulltext":true,"cited_by_count":144,"citation_normalized_percentile":{"value":0.9825784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"5628","last_page":"5635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995999932289124,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.6960929036140442},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6149604916572571},{"id":"https://openalex.org/keywords/flowchart","display_name":"Flowchart","score":0.5707075595855713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5194401144981384},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5046578645706177},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4809957444667816},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4746739864349365},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4200165867805481},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41583168506622314},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3550516963005066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11301356554031372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6960929036140442},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6149604916572571},{"id":"https://openalex.org/C72041958","wikidata":"https://www.wikidata.org/wiki/Q185092","display_name":"Flowchart","level":2,"score":0.5707075595855713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194401144981384},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5046578645706177},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4809957444667816},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4746739864349365},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4200165867805481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41583168506622314},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3550516963005066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11301356554031372},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33015628","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015628","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4506/4384","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33015628","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015628","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4506/4384","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5370663006","display_name":null,"funder_award_id":"N00014-15-1-2356","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7861924171","display_name":null,"funder_award_id":"CCF-1317376","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7931865478","display_name":null,"funder_award_id":"4-15-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8324445706","display_name":null,"funder_award_id":"1317376","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903707108.pdf","grobid_xml":"https://content.openalex.org/works/W2903707108.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W845365781","https://openalex.org/W1536680647","https://openalex.org/W1576445103","https://openalex.org/W1606858007","https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W1903029394","https://openalex.org/W1959000896","https://openalex.org/W1975517671","https://openalex.org/W2061851712","https://openalex.org/W2062118960","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2152161678","https://openalex.org/W2155541015","https://openalex.org/W2163605009","https://openalex.org/W2171061940","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2311110368","https://openalex.org/W2412782625","https://openalex.org/W2553303224","https://openalex.org/W2592691248","https://openalex.org/W2604414494","https://openalex.org/W2613718673","https://openalex.org/W2619184049","https://openalex.org/W2739879705","https://openalex.org/W2753276755","https://openalex.org/W2753783593","https://openalex.org/W2765407302","https://openalex.org/W2778955544","https://openalex.org/W2782417188","https://openalex.org/W2803023299","https://openalex.org/W2949117887","https://openalex.org/W2951696358","https://openalex.org/W2953070460","https://openalex.org/W2962971773","https://openalex.org/W2963420686","https://openalex.org/W2963446712","https://openalex.org/W2963628712","https://openalex.org/W2963687836","https://openalex.org/W2964222566","https://openalex.org/W3118608800","https://openalex.org/W4250737575","https://openalex.org/W4294375521","https://openalex.org/W4297798436","https://openalex.org/W4308909683","https://openalex.org/W4309845474","https://openalex.org/W6600281463","https://openalex.org/W6623430341","https://openalex.org/W6631782140","https://openalex.org/W6634343353","https://openalex.org/W6665999328","https://openalex.org/W6676297131","https://openalex.org/W6682980823","https://openalex.org/W6685405407","https://openalex.org/W6687483927","https://openalex.org/W6697978515","https://openalex.org/W6725739302","https://openalex.org/W6728250325","https://openalex.org/W6737496325","https://openalex.org/W6743731764","https://openalex.org/W6747306630","https://openalex.org/W6747570768","https://openalex.org/W6751751081"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4205958290","https://openalex.org/W1521353230"],"abstract_inverted_index":{"We":[0],"focus":[1],"on":[2,186],"the":[3,21,29,44,75,79,109,136,149,153,169,179,195,201,225],"problem":[4,69],"of":[5,40,73,181,227],"training":[6,78],"a":[7,52,71,86,96,102,120,140,156,204],"deep":[8],"neural":[9],"network":[10,23,26,197],"in":[11,17,43,77,92],"generations.":[12],"The":[13,123],"flowchart":[14],"is":[15,32,125],"that,":[16],"order":[18],"to":[19,37,51,95,112,135,144,148,171],"optimize":[20],"target":[22],"(student),":[24],"another":[25],"(teacher)":[27],"with":[28,128],"same":[30],"architecture":[31],"first":[33],"trained,":[34],"and":[35,146,164,176,192,208,219],"used":[36,85],"provide":[38],"part":[39],"supervision":[41,158],"signals":[42],"next":[45],"stage.":[46],"While":[47],"this":[48,68,117],"strategy":[49],"leads":[50],"higher":[53,211],"accuracy,":[54,104],"many":[55],"aspects":[56],"(e.g.,":[57,89],"why":[58],"teacher-student":[59],"optimization":[60],"helps)":[61],"still":[62],"need":[63],"further":[64],"explorations.This":[65],"paper":[66],"studies":[67],"from":[70,173],"perspective":[72],"controlling":[74],"strictness":[76],"teacher":[80,98,110,137,154,196],"network.":[81],"Existing":[82],"approaches":[83],"mostly":[84],"hard":[87],"distribution":[88],"one-hot":[90],"vectors)":[91],"training,":[93],"leading":[94],"strict":[97],"which":[99],"itself":[100],"has":[101],"high":[103],"but":[105],"we":[106],"argue":[107],"that":[108],"needs":[111],"be":[113],"more":[114],"tolerant,":[115],"although":[116],"often":[118],"implies":[119],"lower":[121,178],"accuracy.":[122],"implementation":[124],"very":[126],"easy,":[127],"merely":[129],"an":[130],"extra":[131],"loss":[132],"term":[133],"added":[134],"network,":[138],"facilitating":[139],"few":[141],"secondary":[142],"classes":[143],"emerge":[145],"complement":[147],"primary":[150],"class.":[151],"Consequently,":[152],"provides":[155],"milder":[157],"signal":[159],"(a":[160],"less":[161,199],"peaked":[162],"distribution),":[163],"makes":[165],"it":[166],"possible":[167],"for":[168],"student":[170],"learn":[172],"inter-class":[174],"similarity":[175],"potentially":[177],"risk":[180],"over-fitting.":[182],"Experiments":[183],"are":[184],"performed":[185],"standard":[187],"image":[188],"classification":[189,212],"tasks":[190],"(CIFAR100":[191],"ILSVRC2012).":[193],"Although":[194],"behaves":[198],"powerful,":[200],"students":[202],"show":[203],"persistent":[205],"ability":[206],"growth":[207],"eventually":[209],"achieve":[210],"accuracies":[213],"than":[214],"other":[215],"competitors.":[216],"Model":[217],"ensemble":[218],"transfer":[220],"feature":[221],"extraction":[222],"also":[223],"verify":[224],"effectiveness":[226],"our":[228],"approach.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}