{"id":"https://openalex.org/W3168114125","doi":"https://doi.org/10.1145/3447548.3467198","title":"On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition","display_name":"On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3168114125","doi":"https://doi.org/10.1145/3447548.3467198","mag":"3168114125"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467198","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090936459","display_name":"Ching-Yuan Bai","orcid":"https://orcid.org/0009-0005-0937-2593"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ching-Yuan Bai","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616524","display_name":"Hsuan-Tien Lin","orcid":"https://orcid.org/0000-0003-2968-0671"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsuan-Tien Lin","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045077843","display_name":"Colin Raffel","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Raffel","raw_affiliation_strings":["Google, Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"Google, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070689858","display_name":"Wendy Kan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wendy Chi-wen Kan","raw_affiliation_strings":["Google, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090936459"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":2.0346,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.8867475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2534","last_page":"2542"},"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":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.989799976348877,"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/memorization","display_name":"Memorization","score":0.8809117078781128},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7823643684387207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7232373356819153},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6453585028648376},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6410897970199585},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6363919377326965},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5667436718940735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5381473302841187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4965854287147522},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41730186343193054},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12296536564826965},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11736398935317993},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.08717533946037292}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.8809117078781128},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7823643684387207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232373356819153},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6453585028648376},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6410897970199585},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6363919377326965},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5667436718940735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381473302841187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4965854287147522},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41730186343193054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12296536564826965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11736398935317993},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.08717533946037292},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467198","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.03062","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.03062","pdf_url":"https://arxiv.org/pdf/2106.03062","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3447548.3467198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467198","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3168114125.pdf","grobid_xml":"https://content.openalex.org/works/W3168114125.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2919042","https://openalex.org/W299440670","https://openalex.org/W1583912456","https://openalex.org/W1909320841","https://openalex.org/W2097117768","https://openalex.org/W2099057450","https://openalex.org/W2099471712","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2173520492","https://openalex.org/W2183341477","https://openalex.org/W2411541852","https://openalex.org/W2412320034","https://openalex.org/W2432004435","https://openalex.org/W2553303224","https://openalex.org/W2605287558","https://openalex.org/W2739748921","https://openalex.org/W2766527293","https://openalex.org/W2782980316","https://openalex.org/W2785678896","https://openalex.org/W2819579046","https://openalex.org/W2893749619","https://openalex.org/W2913002991","https://openalex.org/W2947590261","https://openalex.org/W2949117887","https://openalex.org/W2949416428","https://openalex.org/W2950893734","https://openalex.org/W2950946978","https://openalex.org/W2951004968","https://openalex.org/W2953318193","https://openalex.org/W2962770929","https://openalex.org/W2962974533","https://openalex.org/W2963185411","https://openalex.org/W2963470893","https://openalex.org/W2963981733","https://openalex.org/W2964081807","https://openalex.org/W2964318046","https://openalex.org/W2970241862","https://openalex.org/W2982763192","https://openalex.org/W2995327724","https://openalex.org/W2997856340","https://openalex.org/W2999866101","https://openalex.org/W3015304056","https://openalex.org/W3042816398","https://openalex.org/W4234552385","https://openalex.org/W4301409532","https://openalex.org/W6601048975"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2803139007","https://openalex.org/W2088647418","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2151687600"],"abstract_inverted_index":{"Many":[0],"recent":[1],"developments":[2],"on":[3,11,169],"generative":[4,53,77,144,171],"models":[5,121,155],"for":[6,117],"natural":[7],"images":[8,148],"have":[9],"relied":[10],"heuristically-motivated":[12],"metrics":[13,47],"that":[14,102,133],"can":[15],"be":[16],"easily":[17],"gamed":[18],"by":[19,48],"memorizing":[20],"a":[21,30,52,92,137],"small":[22],"sample":[23],"from":[24],"the":[25,35,43,85,115,118],"true":[26],"distribution":[27],"or":[28],"training":[29],"model":[31],"directly":[32],"to":[33,69,100,122,160,165],"improve":[34],"metric.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,83,112],"critically":[41],"evaluate":[42],"gameability":[44],"of":[45,128,153],"these":[46],"designing":[49],"and":[50,73,96,124,139,149],"deploying":[51],"modeling":[54],"competition.":[55],"Our":[56,130],"competition":[57],"received":[58],"over":[59],"11000":[60],"submitted":[61],"models.":[62,145,172],"The":[63,146],"competitiveness":[64],"between":[65],"participants":[66],"allowed":[67],"us":[68],"investigate":[70],"both":[71],"intentional":[72,81],"unintentional":[74,134],"memorization":[75,135,151],"in":[76,108,142],"modeling.":[78],"To":[79],"detect":[80],"memorization,":[82],"propose":[84],"\"Memorization-Informed":[86],"Frechet":[87],"Inception":[88],"Distance\"":[89],"(MiFID)":[90],"as":[91,156,158],"new":[93],"memorization-aware":[94],"metric":[95],"design":[97],"benchmark":[98],"procedures":[99],"ensure":[101],"winning":[103],"submissions":[104],"made":[105],"genuine":[106],"improvements":[107],"perceptual":[109],"quality.":[110],"Furthermore,":[111],"manually":[113],"inspect":[114],"code":[116,159],"1000":[119],"top-performing":[120],"understand":[123],"label":[125],"different":[126],"forms":[127],"memorization.":[129],"analysis":[131],"reveals":[132],"is":[136],"serious":[138],"common":[140],"issue":[141],"popular":[143],"generated":[147],"our":[150],"labels":[152],"those":[154],"well":[157],"compute":[161],"MiFID":[162],"are":[163],"released":[164],"facilitate":[166],"future":[167],"studies":[168],"benchmarking":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-06-22T00:00:00"}