{"id":"https://openalex.org/W2998106940","doi":"https://doi.org/10.1609/aaai.v34i04.5940","title":"Structured Output Learning with Conditional Generative Flows","display_name":"Structured Output Learning with Conditional Generative Flows","publication_year":2020,"publication_date":"2020-04-03","ids":{"openalex":"https://openalex.org/W2998106940","doi":"https://doi.org/10.1609/aaai.v34i04.5940","mag":"2998106940"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v34i04.5940","doi":"https://doi.org/10.1609/aaai.v34i04.5940","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i04.5940","pdf_url":null,"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,"listed_in":["jufo-2","norway-1"],"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v34i04.5940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032483127","display_name":"You Li Lu","orcid":"https://orcid.org/0000-0002-4357-1888","observed_orcids":["https://orcid.org/0000-0002-4357-1888"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Lu","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002044887","display_name":"Bert Huang","orcid":"https://orcid.org/0000-0002-8548-7246","observed_orcids":["https://orcid.org/0000-0002-8548-7246"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bert Huang","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":2.4794,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.91562047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"34","issue":"04","first_page":"5005","last_page":"5012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.16660000383853912,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.16660000383853912,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.15629999339580536,"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/T10028","display_name":"Topic Modeling","score":0.15000000596046448,"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/structured-prediction","display_name":"structured prediction","score":0.8050000071525574},{"id":"https://openalex.org/keywords/flow-based-generative-models","display_name":"flow-based generative models","score":0.7260000109672546},{"id":"https://openalex.org/keywords/conditional-sampling","display_name":"conditional sampling","score":0.4869999885559082}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7834126353263855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6081991195678711},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5450050234794617},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5133029818534851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4920003116130829},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.48534145951271057},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4364669919013977},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4326103925704956},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.41021257638931274},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36354273557662964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.273023784160614},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16269508004188538},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v34i04.5940","doi":"https://doi.org/10.1609/aaai.v34i04.5940","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i04.5940","pdf_url":null,"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,"listed_in":["jufo-2","norway-1"],"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"},{"id":"pmh:oai:arXiv.org:1905.13288","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13288","pdf_url":"https://arxiv.org/pdf/1905.13288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/5940","doi":null,"is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/5940","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5940/5796","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1905.13288","doi":"https://doi.org/10.48550/arxiv.1905.13288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.13288","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v34i04.5940","doi":"https://doi.org/10.1609/aaai.v34i04.5940","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i04.5940","pdf_url":null,"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,"listed_in":["jufo-2","norway-1"],"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2998106940.pdf","grobid_xml":"https://content.openalex.org/works/W2998106940.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W114565888","https://openalex.org/W299440670","https://openalex.org/W1522301498","https://openalex.org/W1583912456","https://openalex.org/W1834627138","https://openalex.org/W1903029394","https://openalex.org/W1959608418","https://openalex.org/W1987648924","https://openalex.org/W2042801185","https://openalex.org/W2056370875","https://openalex.org/W2099057450","https://openalex.org/W2110158442","https://openalex.org/W2114096665","https://openalex.org/W2120340025","https://openalex.org/W2124592697","https://openalex.org/W2130184048","https://openalex.org/W2130975789","https://openalex.org/W2136064009","https://openalex.org/W2147880316","https://openalex.org/W2154791445","https://openalex.org/W2158844819","https://openalex.org/W2161236525","https://openalex.org/W2188365844","https://openalex.org/W2226771013","https://openalex.org/W2276303159","https://openalex.org/W2395611524","https://openalex.org/W2409550820","https://openalex.org/W2508457857","https://openalex.org/W2508728158","https://openalex.org/W2553718801","https://openalex.org/W2587284713","https://openalex.org/W2599275287","https://openalex.org/W2604538595","https://openalex.org/W2619016545","https://openalex.org/W2785442381","https://openalex.org/W2786449553","https://openalex.org/W2796426718","https://openalex.org/W2808746463","https://openalex.org/W2819579046","https://openalex.org/W2890492372","https://openalex.org/W2895434480","https://openalex.org/W2911827218","https://openalex.org/W2912298597","https://openalex.org/W2912618358","https://openalex.org/W2912961385","https://openalex.org/W2928160594","https://openalex.org/W2949847548","https://openalex.org/W2951004968","https://openalex.org/W2963047245","https://openalex.org/W2963090522","https://openalex.org/W2963139417","https://openalex.org/W2963315679","https://openalex.org/W2963755523","https://openalex.org/W2963917315","https://openalex.org/W2963962369","https://openalex.org/W2964076774","https://openalex.org/W2964121744","https://openalex.org/W2964205912","https://openalex.org/W3043547428","https://openalex.org/W4210678508","https://openalex.org/W4288616984","https://openalex.org/W4293052541","https://openalex.org/W4293849739","https://openalex.org/W6679447461","https://openalex.org/W6752910514"],"related_works":["https://openalex.org/W2913117037","https://openalex.org/W7096218252","https://openalex.org/W4293329556","https://openalex.org/W3035686681","https://openalex.org/W7095514212","https://openalex.org/W2965450789","https://openalex.org/W2819579046","https://openalex.org/W2969858779","https://openalex.org/W1583363831","https://openalex.org/W2098708428"],"abstract_inverted_index":{"Traditional":[0],"structured":[1,18,66,163],"prediction":[2,111,164],"models":[3,35,76],"try":[4],"to":[5,12,39,50,77,118,160],"learn":[6],"the":[7,14,17,22,30,42,72,136,147],"conditional":[8,58,62,105],"likelihood,":[9],"i.e.,":[10],"p(y|x),":[11],"capture":[13],"relationship":[15],"between":[16],"output":[19,67],"y":[20],"and":[21,81,102,121,142,157],"input":[23],"features":[24],"x.":[25],"For":[26],"many":[27,161],"models,":[28],"computing":[29],"likelihood":[31],"is":[32,155,158],"intractable.":[33],"These":[34],"are":[36],"therefore":[37],"hard":[38],"train,":[40],"requiring":[41],"use":[43,115],"of":[44,74],"surrogate":[45,90],"objectives":[46],"or":[47,92],"variational":[48],"inference":[49,94],"approximate":[51],"likelihood.":[52],"In":[53,124],"this":[54,116],"paper,":[55],"we":[56,99,127],"propose":[57],"Glow":[59],"(c-Glow),":[60],"a":[61,89,109],"generative":[63],"flow":[64],"for":[65],"learning.":[68],"C-Glow":[69,134],"benefits":[70],"from":[71],"ability":[73],"flow-based":[75],"compute":[78],"p(y|x":[79],"exactly":[80],"efficiently.":[82],"Learning":[83],"with":[84],"c-Glow":[85,129,154],"does":[86],"not":[87],"require":[88],"objective":[91],"performing":[93],"during":[95],"training.":[96],"Once":[97],"trained,":[98],"can":[100,114],"directly":[101],"efficiently":[103],"generate":[104],"samples.":[106],"We":[107],"develop":[108],"sample-based":[110],"method,":[112],"which":[113],"advantage":[117],"do":[119],"efficient":[120],"effective":[122],"inference.":[123],"our":[125],"experiments,":[126],"test":[128],"on":[130],"five":[131],"different":[132,162],"tasks.":[133,149],"outperforms":[135],"state-of-the-art":[137],"baselines":[138],"in":[139,146],"some":[140],"tasks":[141],"predicts":[143],"comparable":[144],"outputs":[145],"other":[148],"The":[150],"results":[151],"show":[152],"that":[153],"versatile":[156],"applicable":[159],"problems.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2020-01-10T00:00:00"}