{"id":"https://openalex.org/W3206203767","doi":null,"title":"Identifiable Variational Autoencoders via Sparse Decoding.","display_name":"Identifiable Variational Autoencoders via Sparse Decoding.","publication_year":2021,"publication_date":"2021-10-20","ids":{"openalex":"https://openalex.org/W3206203767","mag":"3206203767"},"language":"en","primary_location":{"id":"mag:3206203767","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.10804","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.10804","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030371889","display_name":"Gemma E. Moran","orcid":"https://orcid.org/0000-0002-4438-6350","observed_orcids":["https://orcid.org/0000-0002-4438-6350"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gemma E. Moran","raw_affiliation_strings":["Columbia University"],"raw_orcid":"https://orcid.org/0000-0002-4438-6350","affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109398524","display_name":"Dhanya Sridhar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhanya Sridhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934111","display_name":"Zhaoran Wang","orcid":"https://orcid.org/0000-0002-6617-4842","observed_orcids":["https://orcid.org/0000-0002-6617-4842","https://orcid.org/0000-0002-2789-7909"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoran Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6617-4842","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070920982","display_name":"David M. Blei","orcid":"https://orcid.org/0000-0002-5588-4611","observed_orcids":["https://orcid.org/0000-0002-5588-4611"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David M. Blei","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5588-4611","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10028","display_name":"Topic Modeling","score":0.7095000147819519,"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/T10028","display_name":"Topic Modeling","score":0.7095000147819519,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.11569999903440475,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.025800000876188278,"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/identifiability","display_name":"identifiability","score":0.9300000071525574},{"id":"https://openalex.org/keywords/latent-factor-models","display_name":"latent factor models","score":0.7670000195503235},{"id":"https://openalex.org/keywords/unsupervised-representation-learning","display_name":"unsupervised feature learning","score":0.9010000228881836},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.7839999794960022},{"id":"https://openalex.org/keywords/variational-em","display_name":"variational EM","score":0.843999981880188},{"id":"https://openalex.org/keywords/deep-generative-models","display_name":"deep generative models","score":0.7429999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579149961471558},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.6098432540893555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978339910507202},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5953817963600159},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5660285949707031},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5473785400390625},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5300011038780212},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.52094566822052},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4914599657058716},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4912084937095642},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4752649664878845},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45231950283050537},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39466679096221924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3559797406196594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23338457942008972},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3206203767","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.10804","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3206203767","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.10804","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1625086225","https://openalex.org/W1880262756","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1979283544","https://openalex.org/W2016229608","https://openalex.org/W2029721016","https://openalex.org/W2104316038","https://openalex.org/W2105617746","https://openalex.org/W2120865735","https://openalex.org/W2128002512","https://openalex.org/W2140318696","https://openalex.org/W2163922914","https://openalex.org/W2187089797","https://openalex.org/W2219888463","https://openalex.org/W2403726878","https://openalex.org/W2514253892","https://openalex.org/W2566065221","https://openalex.org/W2753738274","https://openalex.org/W2759710969","https://openalex.org/W2785961484","https://openalex.org/W2886348436","https://openalex.org/W2901677030","https://openalex.org/W2903538854","https://openalex.org/W2909699200","https://openalex.org/W2956607501","https://openalex.org/W2963085847","https://openalex.org/W2964121744","https://openalex.org/W2964211782","https://openalex.org/W2996554397","https://openalex.org/W3015492498","https://openalex.org/W3049025113","https://openalex.org/W3166680982","https://openalex.org/W4403243319"],"related_works":["https://openalex.org/W4300947078","https://openalex.org/W2909699200","https://openalex.org/W4295096240","https://openalex.org/W7133237203","https://openalex.org/W4394827787","https://openalex.org/W3165347936","https://openalex.org/W2892210823","https://openalex.org/W3129088656","https://openalex.org/W2914441330","https://openalex.org/W2779959161"],"abstract_inverted_index":{"We":[0,97,166,191],"develop":[1],"the":[2,21,39,45,56,101,110,135,155,172,182],"Sparse":[3,22,102,173,183],"VAE,":[4],"a":[5,17,25,52,70,82,93,114,146],"deep":[6],"generative":[7],"model":[8,35],"for":[9,141],"unsupervised":[10],"representation":[11],"learning":[12],"on":[13,51,151],"high-dimensional":[14],"data.":[15,190],"Given":[16],"dataset":[18,46],"of":[19,27,44,55,118,137],"observations,":[20],"VAE":[23,103,174,184],"learns":[24],"set":[26,117],"latent":[28,57,197],"factors":[29,198],"that":[30,41,100,148,152,193],"captures":[31],"its":[32],"distribution.":[33],"The":[34,128],"is":[36,66,78,89,104,134],"sparse":[37],"in":[38,61,73,85,91,164],"sense":[40],"each":[42,48,64,76,87,142],"feature":[43,147],"(i.e.,":[47],"dimension)":[49],"depends":[50,149],"small":[53],"subset":[54],"factors.":[58,119],"As":[59],"examples,":[60],"ratings":[62],"data":[63,75,107],"movie":[65],"only":[67,79,92,150],"described":[68],"by":[69],"few":[71,83,94],"genres;":[72],"text":[74],"word":[77],"applicable":[80],"to":[81,161,170],"topics;":[84],"genomics,":[86],"gene":[88],"active":[90],"biological":[95],"processes.":[96],"first":[98],"show":[99,168],"identifiable:":[105],"given":[106],"drawn":[108],"from":[109],"model,":[111],"there":[112,144],"exists":[113,145],"uniquely":[115],"optimal":[116],"(In":[120],"contrast,":[121],"most":[122],"VAE-based":[123],"models":[124],"are":[125],"not":[126,159],"identifiable.)":[127],"key":[129],"assumption":[130],"behind":[131],"Sparse-VAE":[132],"identifiability":[133],"existence":[136],"anchor":[156],"features,":[139],"where":[140],"factor":[143],"factor.":[153],"Importantly,":[154],"features":[157],"do":[158],"need":[160],"be":[162],"known":[163],"advance.":[165],"then":[167],"how":[169],"fit":[171],"with":[175,185],"variational":[176],"EM.":[177],"Finally,":[178],"we":[179],"empirically":[180],"study":[181],"both":[186],"simulated":[187],"and":[188,199],"real":[189],"find":[192],"it":[194],"recovers":[195],"meaningful":[196],"has":[200],"smaller":[201],"heldout":[202],"reconstruction":[203],"error":[204],"than":[205],"related":[206],"methods.":[207]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-10-25T00:00:00"}