{"id":"https://openalex.org/W4290927734","doi":"https://doi.org/10.1145/3534678.3539291","title":"Learning Optimal Priors for Task-Invariant Representations in Variational Autoencoders","display_name":"Learning Optimal Priors for Task-Invariant Representations in Variational Autoencoders","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290927734","doi":"https://doi.org/10.1145/3534678.3539291"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539291","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5069398453","display_name":"Hiroshi Takahashi","orcid":"https://orcid.org/0000-0001-5288-6729"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroshi Takahashi","raw_affiliation_strings":["NTT, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034538103","display_name":"Tomoharu Iwata","orcid":"https://orcid.org/0000-0003-4425-1971"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoharu Iwata","raw_affiliation_strings":["NTT, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030880294","display_name":"Atsutoshi Kumagai","orcid":"https://orcid.org/0000-0002-2915-4615"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsutoshi Kumagai","raw_affiliation_strings":["NTT, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010327448","display_name":"Sekitoshi Kanai","orcid":"https://orcid.org/0000-0003-4383-4454"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sekitoshi Kanai","raw_affiliation_strings":["NTT, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037036505","display_name":"Masanori Yamada","orcid":"https://orcid.org/0000-0002-6493-8554"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanori Yamada","raw_affiliation_strings":["NTT, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047686471","display_name":"Yuuki Yamanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuuki Yamanaka","raw_affiliation_strings":["NTT, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031707680","display_name":"Hisashi Kashima","orcid":"https://orcid.org/0000-0002-2770-0184"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kashima","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069398453"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57259064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1739","last_page":"1748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9987999796867371,"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":0.9882000088691711,"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/latent-variable","display_name":"Latent variable","score":0.7699452638626099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6465033292770386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5916845202445984},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5573263168334961},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5243428349494934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49777868390083313},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.49460670351982117},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4541161060333252},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.44031789898872375},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.4207095503807068},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39591947197914124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2386344075202942},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.19274255633354187},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18077218532562256}],"concepts":[{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.7699452638626099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465033292770386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916845202445984},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5573263168334961},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5243428349494934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49777868390083313},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.49460670351982117},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4541161060333252},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.44031789898872375},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.4207095503807068},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39591947197914124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2386344075202942},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.19274255633354187},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18077218532562256},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539291","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W91088564","https://openalex.org/W395933519","https://openalex.org/W1583837637","https://openalex.org/W1920962657","https://openalex.org/W2100659887","https://openalex.org/W2112796928","https://openalex.org/W2125865219","https://openalex.org/W2187089797","https://openalex.org/W2492827599","https://openalex.org/W2593390416","https://openalex.org/W2607662938","https://openalex.org/W2949649223","https://openalex.org/W2962691331","https://openalex.org/W2962850167","https://openalex.org/W2962897020","https://openalex.org/W2963223306","https://openalex.org/W3112335585","https://openalex.org/W3127854286","https://openalex.org/W4236965008","https://openalex.org/W4300011764"],"related_works":["https://openalex.org/W4287995534","https://openalex.org/W2998168123","https://openalex.org/W2897995864","https://openalex.org/W2292254049","https://openalex.org/W2592385986","https://openalex.org/W4281924768","https://openalex.org/W3099179464","https://openalex.org/W2772780115","https://openalex.org/W3041775337","https://openalex.org/W2773028880"],"abstract_inverted_index":{"The":[0],"variational":[1],"autoencoder":[2],"(VAE)":[3],"is":[4,37,69,76,147],"a":[5,157],"powerful":[6],"latent":[7,52,61,90,95],"variable":[8,62,91,96],"model":[9],"for":[10,161],"unsupervised":[11],"representation":[12,116,177],"learning.":[13],"However,":[14,113],"it":[15],"does":[16,117],"not":[17,118],"work":[18,108,119],"well":[19,120,179],"in":[20,30],"case":[21],"of":[22,59,149,200],"insufficient":[23],"data":[24,65],"points.":[25],"To":[26,102],"improve":[27],"the":[28,33,50,55,57,60,64,72,79,89,94,100,106,122,132,137,142,150,163,172,181,198],"performance":[29],"such":[31,204],"situations,":[32],"conditional":[34],"VAE":[35],"(CVAE)":[36],"widely":[38],"used,":[39],"which":[40,75,196],"aims":[41],"to":[42],"share":[43],"task-invariant":[44,51,73,194],"knowledge":[45],"with":[46],"multiple":[47],"tasks":[48],"through":[49],"variable.":[53],"In":[54,125,165],"CVAE,":[56],"posterior":[58],"given":[63],"point":[66],"and":[67,92,139,208],"task":[68],"regularized":[70],"by":[71,78],"prior,":[74],"modeled":[77],"standard":[80,144],"Gaussian":[81,145],"distribution.":[82],"Although":[83],"this":[84,104,126],"regularization":[85],"encourages":[86],"independence":[87],"between":[88],"task,":[93],"remains":[97],"dependent":[98],"on":[99,121,153,180,185],"task.":[101],"reduce":[103,136],"task-dependency,":[105],"previous":[107,173],"introduced":[109],"an":[110],"additional":[111],"regularizer.":[112],"its":[114],"learned":[115,176],"target":[123,182],"tasks.":[124,183],"study,":[127],"we":[128,155,167],"theoretically":[129,168],"investigate":[130],"why":[131],"CVAE":[133],"cannot":[134],"sufficiently":[135],"task-dependency":[138],"show":[140,169,188],"that":[141,170,189],"simple":[143],"prior":[146,160],"one":[148],"causes.":[151],"Based":[152],"this,":[154],"propose":[156],"theoretical":[158],"optimal":[159],"reducing":[162],"task-dependency.":[164],"addition,":[166],"unlike":[171],"work,":[174],"our":[175,190],"works":[178],"Experiments":[184],"various":[186,201],"datasets":[187],"approach":[191],"obtains":[192],"better":[193],"representations,":[195],"improves":[197],"performances":[199],"downstream":[202],"applications":[203],"as":[205],"density":[206],"estimation":[207],"classification.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}