{"id":"https://openalex.org/W4378713411","doi":"https://doi.org/10.48550/arxiv.2305.16543","title":"Revisiting Structured Variational Autoencoders","display_name":"Revisiting Structured Variational Autoencoders","publication_year":2023,"publication_date":"2023-05-25","ids":{"openalex":"https://openalex.org/W4378713411","doi":"https://doi.org/10.48550/arxiv.2305.16543"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.16543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.16543","pdf_url":"https://arxiv.org/pdf/2305.16543","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.16543","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101207356","display_name":"Yixiu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yixiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054079047","display_name":"Scott W. Linderman","orcid":"https://orcid.org/0000-0002-3878-9073"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linderman, Scott W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9952999949455261,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9833999872207642,"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/leverage","display_name":"Leverage (statistics)","score":0.8021745681762695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7876464128494263},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6889844536781311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6511964797973633},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.6444812417030334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6021150350570679},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5035445094108582},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.499326229095459},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.47392091155052185},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.4496413767337799},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4480144679546356},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43559059500694275},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4022822976112366},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.19415238499641418}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8021745681762695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876464128494263},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6889844536781311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6511964797973633},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.6444812417030334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6021150350570679},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5035445094108582},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.499326229095459},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.47392091155052185},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.4496413767337799},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4480144679546356},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43559059500694275},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4022822976112366},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.19415238499641418}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.16543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.16543","pdf_url":"https://arxiv.org/pdf/2305.16543","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.16543","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.16543","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.16543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.16543","pdf_url":"https://arxiv.org/pdf/2305.16543","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5276531441","display_name":null,"funder_award_id":"U19NS113201","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G955004149","display_name":null,"funder_award_id":"R01NS113119","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378713411.pdf","grobid_xml":"https://content.openalex.org/works/W4378713411.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2988134182","https://openalex.org/W3091320577","https://openalex.org/W2106257677","https://openalex.org/W2964321162","https://openalex.org/W4322716735","https://openalex.org/W2152895903","https://openalex.org/W2070797946","https://openalex.org/W4301430456","https://openalex.org/W2890980249","https://openalex.org/W2089823622"],"abstract_inverted_index":{"Structured":[0],"variational":[1,174],"autoencoders":[2],"(SVAEs)":[3],"combine":[4],"probabilistic":[5],"graphical":[6],"model":[7],"priors":[8],"on":[9,136],"latent":[10,17],"variables,":[11],"deep":[12],"neural":[13],"networks":[14],"to":[15,19,53,155,171],"link":[16],"variables":[18],"observed":[20],"data,":[21,36,149],"and":[22,55,73,86,98,128,150],"structure-exploiting":[23],"algorithms":[24,105],"for":[25,34,94],"approximate":[26],"posterior":[27,129],"inference.":[28],"These":[29],"models":[30,127],"are":[31],"particularly":[32],"appealing":[33],"sequential":[35],"where":[37],"the":[38,102,107,110,120,122,143,167],"prior":[39],"can":[40,145],"capture":[41],"temporal":[42],"dependencies.":[43],"However,":[44],"despite":[45],"their":[46,75],"conceptual":[47],"elegance,":[48],"SVAEs":[49,67],"have":[50,59],"proven":[51],"difficult":[52],"implement,":[54],"more":[56,78,125],"general":[57,79],"approaches":[58],"been":[60],"favored":[61],"in":[62,81,119],"practice.":[63],"Here,":[64],"we":[65,89,113,140,151],"revisit":[66,172],"using":[68],"modern":[69,92],"machine":[70],"learning":[71],"tools":[72],"demonstrate":[74],"advantages":[76],"over":[77],"alternatives":[80],"terms":[82],"of":[83,101,109],"both":[84],"accuracy":[85],"efficiency.":[87],"First,":[88],"develop":[90,156],"a":[91,157],"implementation":[93],"hardware":[95],"acceleration,":[96],"parallelization,":[97],"automatic":[99],"differentiation":[100],"message":[103],"passing":[104],"at":[106],"core":[108],"SVAE.":[111],"Second,":[112],"show":[114,141,165],"that":[115,166],"by":[116],"exploiting":[117],"structure":[118],"prior,":[121],"SVAE":[123,144],"learns":[124],"accurate":[126],"distributions,":[130],"which":[131],"translate":[132],"into":[133],"improved":[134],"performance":[135],"prediction":[137],"tasks.":[138],"Third,":[139],"how":[142],"naturally":[146],"handle":[147],"missing":[148],"leverage":[152],"this":[153],"ability":[154],"novel,":[158],"self-supervised":[159],"training":[160],"approach.":[161],"Altogether,":[162],"these":[163],"results":[164],"time":[168],"is":[169],"ripe":[170],"structured":[173],"autoencoders.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}