{"id":"https://openalex.org/W2995256665","doi":null,"title":"You Only Train Once: Loss-Conditional Training of Deep Networks","display_name":"You Only Train Once: Loss-Conditional Training of Deep Networks","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995256665","mag":"2995256665"},"language":"en","primary_location":{"id":"mag:2995256665","doi":null,"is_oa":false,"landing_page_url":"https://www.openreview.net/pdf?id=HyxY6JHKwr","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","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/A5090113830","display_name":"Alexey Dosovitskiy","orcid":"https://orcid.org/0000-0003-1851-0976","observed_orcids":["https://orcid.org/0000-0003-1851-0976"]},"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":"Alexey Dosovitskiy","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":"https://orcid.org/0000-0003-1851-0976","affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010814788","display_name":"Josip Djolonga","orcid":null,"observed_orcids":[]},"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":"Josip Djolonga","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.1073,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.93568972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.5253999829292297,"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":0.5253999829292297,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2199999988079071,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0778999999165535,"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/loss-distribution","display_name":"loss distribution","score":0.4729999899864197},{"id":"https://openalex.org/keywords/loss-weighting","display_name":"loss weighting","score":0.6209999918937683},{"id":"https://openalex.org/keywords/beta-vae","display_name":"beta-VAE","score":0.9679999947547913},{"id":"https://openalex.org/keywords/learned-image-compression","display_name":"learned image compression","score":0.9869999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452758550643921},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6224185228347778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6185106635093689},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5571601986885071},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5526403784751892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47567692399024963},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4620454013347626},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2995256665","doi":null,"is_oa":false,"landing_page_url":"https://www.openreview.net/pdf?id=HyxY6JHKwr","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1539331983","https://openalex.org/W1686810756","https://openalex.org/W1959608418","https://openalex.org/W1969074599","https://openalex.org/W2108598243","https://openalex.org/W2133853511","https://openalex.org/W2286454943","https://openalex.org/W2475287302","https://openalex.org/W2510182739","https://openalex.org/W2545656684","https://openalex.org/W2553701371","https://openalex.org/W2603777577","https://openalex.org/W2616957565","https://openalex.org/W2620076854","https://openalex.org/W2624871570","https://openalex.org/W2727849499","https://openalex.org/W2753738274","https://openalex.org/W2760103357","https://openalex.org/W2785562966","https://openalex.org/W2791091755","https://openalex.org/W2798512429","https://openalex.org/W2893749619","https://openalex.org/W2901878846","https://openalex.org/W2904367110","https://openalex.org/W2907670343","https://openalex.org/W2913340405","https://openalex.org/W2962848800","https://openalex.org/W2964001908","https://openalex.org/W2964143092","https://openalex.org/W2969510321","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3009448753","https://openalex.org/W4416131796","https://openalex.org/W2804456057","https://openalex.org/W4302011383","https://openalex.org/W2798635843","https://openalex.org/W7133229415","https://openalex.org/W3205956781","https://openalex.org/W3113583495","https://openalex.org/W3123982665","https://openalex.org/W2963402836"],"abstract_inverted_index":{"In":[0],"many":[1],"machine":[2],"learning":[3],"problems,":[4],"loss":[5,79,109],"functions":[6],"are":[7],"weighted":[8],"sums":[9],"of":[10,29,55,90,114],"several":[11],"terms.":[12],"A":[13],"typical":[14],"approach":[15,119],"to":[16,21,39,50,103,107],"dealing":[17],"with":[18,26,123],"these":[19],"is":[20,48,58],"train":[22],"multiple":[23,44,74],"separate":[24],"models":[25,45,75],"different":[27],"selections":[28],"weights":[30],"and":[31,63,130],"then":[32],"either":[33],"choose":[34],"the":[35,111],"best":[36],"one":[37,78],"according":[38],"some":[40],"criterion":[41],"or":[42],"keep":[43],"if":[46],"it":[47],"desirable":[49],"maintain":[51],"a":[52,69,83,88,95],"diverse":[53],"set":[54],"solutions.":[56],"This":[57],"inefficient":[59],"both":[60],"at":[61,64],"training":[62,112],"inference":[65],"time.":[66],"We":[67,116],"propose":[68],"method":[70],"that":[71],"allows":[72],"replacing":[73],"trained":[76,86,97],"on":[77,87,120],"function":[80],"each":[81],"by":[82],"single":[84],"model":[85,96],"distribution":[89,113],"losses.":[91,115],"At":[92],"test":[93],"time":[94],"this":[98,118],"way":[99],"can":[100],"be":[101],"conditioned":[102],"generate":[104],"outputs":[105],"corresponding":[106],"any":[108],"from":[110],"demonstrate":[117],"three":[121],"tasks":[122],"parametrized":[124],"losses:":[125],"beta-VAE,":[126],"learned":[127],"image":[128],"compression,":[129],"fast":[131],"style":[132],"transfer.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":6}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-26T00:00:00"}