{"id":"https://openalex.org/W3185762663","doi":"https://doi.org/10.1109/tpami.2021.3099829","title":"AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks","display_name":"AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3185762663","doi":"https://doi.org/10.1109/tpami.2021.3099829","mag":"3185762663","pmid":"https://pubmed.ncbi.nlm.nih.gov/34310290"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3099829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3099829","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5073271972","display_name":"Yuesong Tian","orcid":"https://orcid.org/0000-0001-6287-4174"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuesong Tian","raw_affiliation_strings":["College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042802004","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-5659-3464"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["JD Explore Academy, Beijing, China","Tencent AI Lab, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108393212","display_name":"Li Shen","orcid":"https://orcid.org/0000-0002-2283-4976"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["JD Explore Academy, Beijing, China","Tencent AI Lab, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014689002","display_name":"Guinan Su","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guinan Su","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634431","display_name":"Zhifeng Li","orcid":"https://orcid.org/0000-0002-9653-7907"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Li","raw_affiliation_strings":["Tencent Data Platform, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Data Platform, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Tencent Data Platform, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent Data Platform, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5073271972"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.9139,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.92558162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"44","issue":"10","first_page":"6752","last_page":"6766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9998999834060669,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9943000078201294,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9922000169754028,"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":0.7336251735687256},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.7250543236732483},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.7166399955749512},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5587874054908752},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5018751621246338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4917927086353302},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.4646657705307007},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.4162311255931854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3542965054512024},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34234756231307983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18982306122779846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336251735687256},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7250543236732483},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7166399955749512},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5587874054908752},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5018751621246338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4917927086353302},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.4646657705307007},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4162311255931854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3542965054512024},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34234756231307983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18982306122779846},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3099829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3099829","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34310290","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34310290","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W34861158","https://openalex.org/W967544008","https://openalex.org/W1522301498","https://openalex.org/W1834627138","https://openalex.org/W2067050450","https://openalex.org/W2194775991","https://openalex.org/W2553303224","https://openalex.org/W2581637843","https://openalex.org/W2593414223","https://openalex.org/W2603777577","https://openalex.org/W2748513770","https://openalex.org/W2785678896","https://openalex.org/W2804078698","https://openalex.org/W2905831066","https://openalex.org/W2906539593","https://openalex.org/W2947996939","https://openalex.org/W2951104886","https://openalex.org/W2952716587","https://openalex.org/W2955096590","https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963684088","https://openalex.org/W2963767194","https://openalex.org/W2963778169","https://openalex.org/W2963800363","https://openalex.org/W2963821229","https://openalex.org/W2964081807","https://openalex.org/W2964444661","https://openalex.org/W2964515685","https://openalex.org/W2965658867","https://openalex.org/W2973943791","https://openalex.org/W2981721547","https://openalex.org/W2982511758","https://openalex.org/W2989221291","https://openalex.org/W2996690341","https://openalex.org/W3034600949","https://openalex.org/W3034720584","https://openalex.org/W3035170495","https://openalex.org/W3035231706","https://openalex.org/W3035574324","https://openalex.org/W3043547428","https://openalex.org/W3099088591","https://openalex.org/W3107781032","https://openalex.org/W3108316907","https://openalex.org/W3108420015","https://openalex.org/W3175491752","https://openalex.org/W4288409632","https://openalex.org/W4294643831","https://openalex.org/W4299412574","https://openalex.org/W4300687381","https://openalex.org/W4300804849","https://openalex.org/W6625168331","https://openalex.org/W6631190155","https://openalex.org/W6685352114","https://openalex.org/W6718092244","https://openalex.org/W6718379498","https://openalex.org/W6729956949","https://openalex.org/W6735677848","https://openalex.org/W6735913928","https://openalex.org/W6743495212","https://openalex.org/W6745560452","https://openalex.org/W6745614327","https://openalex.org/W6746775625","https://openalex.org/W6746914671","https://openalex.org/W6748057086","https://openalex.org/W6748582592","https://openalex.org/W6752378368","https://openalex.org/W6752515464","https://openalex.org/W6755312952","https://openalex.org/W6756685634","https://openalex.org/W6757746634","https://openalex.org/W6759828284","https://openalex.org/W6760905627","https://openalex.org/W6763233178","https://openalex.org/W6763496775","https://openalex.org/W6763832118","https://openalex.org/W6765052341","https://openalex.org/W6765227985","https://openalex.org/W6765779288","https://openalex.org/W6767071290","https://openalex.org/W6767304066","https://openalex.org/W6767953722","https://openalex.org/W6769201011","https://openalex.org/W6769990235","https://openalex.org/W6779093361","https://openalex.org/W6779669310","https://openalex.org/W6780507278","https://openalex.org/W6787910332"],"related_works":["https://openalex.org/W4200062060","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2951149522","https://openalex.org/W3047879910","https://openalex.org/W2888017238","https://openalex.org/W3035580920","https://openalex.org/W4287756212","https://openalex.org/W3185762663"],"abstract_inverted_index":{"Generative":[0],"Adversarial":[1],"Networks":[2],"(GANs)":[3],"are":[4,262],"formulated":[5],"as":[6,86],"minimax":[7,90],"game":[8],"problems":[9],"that":[10,143,163],"generative":[11,257],"networks":[12],"attempt":[13],"to":[14,26,41,50],"approach":[15,131],"real":[16,31],"data":[17],"distributions":[18],"by":[19,60,132],"adversarial":[20,120],"learning":[21,53],"against":[22],"discriminators":[23,115],"which":[24,34,249],"learn":[25],"distinguish":[27],"generated":[28],"samples":[29],"from":[30,54,150],"ones,":[32],"of":[33,57,112,183,202,236,239,246],"the":[35,55,81,109,135,179,191,194,200,227,237,240,244],"intrinsic":[36],"problem":[37],"complexity":[38],"poses":[39],"challenges":[40],"performance":[42],"and":[43,114,159,198,216,243,260],"robustness.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,71],"aim":[49],"boost":[51],"model":[52],"perspective":[56],"network":[58,101,110,196],"architectures,":[59,248],"incorporating":[61],"recent":[62],"progress":[63],"on":[64,108,157,174,193,211,214,218,254],"automated":[65],"architecture":[66,102,148],"search":[67,76,153,180],"into":[68],"GANs.":[69],"Specially":[70],"propose":[72],"a":[73,88,118,129,139,146,175,233],"fully":[74,140],"differentiable":[75,141],"framework,":[77],"dubbed":[78],"alphaGAN,":[79],"where":[80],"searching":[82,241],"process":[83,242],"is":[84],"formalized":[85],"solving":[87],"bi-level":[89],"optimization":[91,127],"problem.":[92],"The":[93,125],"outer-level":[94],"objective":[95,137],"aims":[96],"for":[97,256],"seeking":[98],"an":[99,151],"optimal":[100],"towards":[103],"pure":[104],"Nash":[105],"Equilibrium":[106],"conditioned":[107],"parameters":[111],"generators":[113],"optimized":[116],"with":[117,171,220],"traditional":[119],"loss":[121],"within":[122],"inner":[123],"level.":[124],"entire":[126],"performs":[128],"first-order":[130],"alternately":[133],"minimizing":[134],"two-level":[136],"in":[138,178],"manner":[142],"enables":[144],"obtaining":[145],"suitable":[147],"efficiently":[149],"enormous":[152],"space.":[154],"Extensive":[155],"experiments":[156],"CIFAR-10":[158],"STL-10":[160],"datasets":[161],"show":[162],"our":[164],"algorithm":[165],"can":[166],"obtain":[167],"high-performing":[168],"architectures":[169,255],"only":[170],"3-GPU":[172],"hours":[173],"single":[176],"GPU":[177],"space":[181],"comprised":[182],"approximate":[184],"2\u00d710<sup>11</sup>":[185],"possible":[186],"configurations.":[187],"We":[188,230],"further":[189,252],"validate":[190],"method":[192],"state-of-the-art":[195],"StyleGAN2,":[197],"push":[199],"score":[201],"Fr\u00e9chet":[203],"Inception":[204],"Distance":[205],"(FID)":[206],"further,":[207],"i.e.,":[208],"achieving":[209],"1.94":[210],"CelebA,":[212],"2.86":[213],"LSUN-church":[215],"2.75":[217],"FFHQ,":[219],"relative":[221],"improvements":[222],"3%":[223],"\u223c":[224],"26%":[225],"over":[226],"baseline":[228],"architecture.":[229],"also":[231],"provide":[232],"comprehensive":[234],"analysis":[235],"behavior":[238],"properties":[245],"searched":[247],"would":[250],"benefit":[251],"research":[253],"models.":[258],"Codes":[259],"models":[261],"available":[263],"at":[264],"https://github.com/yuesongtian/AlphaGAN.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}