{"id":"https://openalex.org/W3160874408","doi":null,"title":"Differentially Private Transfer Learning with Conditionally Deep Autoencoders.","display_name":"Differentially Private Transfer Learning with Conditionally Deep Autoencoders.","publication_year":2021,"publication_date":"2021-05-10","ids":{"openalex":"https://openalex.org/W3160874408","mag":"3160874408"},"language":"en","primary_location":{"id":"mag:3160874408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.04615.pdf","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/2105.04615.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046933902","display_name":"Mohit Kumar","orcid":"https://orcid.org/0000-0002-3355-8815","observed_orcids":["https://orcid.org/0000-0002-3355-8815","https://orcid.org/0009-0007-2087-3772","https://orcid.org/0009-0000-5062-504X"]},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mohit Kumar","raw_affiliation_strings":["University of  Rostock"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of  Rostock","institution_ids":["https://openalex.org/I4665924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046933902"],"corresponding_institution_ids":["https://openalex.org/I4665924"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9980000257492065,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0010999999940395355,"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/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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/differential-privacy","display_name":"differential privacy","score":0.8529999852180481},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8069999814033508},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9890000224113464},{"id":"https://openalex.org/keywords/deep-autoencoder","display_name":"deep autoencoder","score":0.8399999737739563},{"id":"https://openalex.org/keywords/fuzzy-membership-functions","display_name":"fuzzy membership functions","score":0.9549999833106995},{"id":"https://openalex.org/keywords/variational-optimization","display_name":"variational optimization","score":0.8050000071525574},{"id":"https://openalex.org/keywords/noise-addition","display_name":"noise addition","score":0.6389999985694885},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.5630000233650208}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.892684280872345},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8654862642288208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271398067474365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5957056879997253},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.569105863571167},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5287332534790039},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5226264595985413},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5194008350372314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46187758445739746},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.45780181884765625},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3844902515411377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36518359184265137},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3160874408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.04615.pdf","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:3160874408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.04615.pdf","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1565176903","https://openalex.org/W1594039573","https://openalex.org/W1731081199","https://openalex.org/W2009668020","https://openalex.org/W2051267297","https://openalex.org/W2090593019","https://openalex.org/W2115358662","https://openalex.org/W2122838776","https://openalex.org/W2129681831","https://openalex.org/W2149466042","https://openalex.org/W2159291411","https://openalex.org/W2159570078","https://openalex.org/W2165157425","https://openalex.org/W2170607218","https://openalex.org/W2279034837","https://openalex.org/W2422697180","https://openalex.org/W2468198418","https://openalex.org/W2473418344","https://openalex.org/W2558385255","https://openalex.org/W2756198004","https://openalex.org/W2782304201","https://openalex.org/W2789226849","https://openalex.org/W2804227495","https://openalex.org/W2903962009","https://openalex.org/W2913413968","https://openalex.org/W2968508074","https://openalex.org/W2987637395","https://openalex.org/W3038283795","https://openalex.org/W3042743947","https://openalex.org/W3092631250","https://openalex.org/W3154347610"],"related_works":["https://openalex.org/W4312219418","https://openalex.org/W4399694512","https://openalex.org/W3042743947","https://openalex.org/W3082856297","https://openalex.org/W6965236529","https://openalex.org/W1977388754","https://openalex.org/W4224928128","https://openalex.org/W2900598269","https://openalex.org/W3206966921","https://openalex.org/W4405893032"],"abstract_inverted_index":{"This":[0],"paper":[1,74],"considers":[2],"the":[3,61,98,102,118,123],"problem":[4],"of":[5,13,33,46,50,63,70,94,101,122],"differentially":[6],"private":[7],"semi-supervised":[8],"transfer":[9,77],"learning.":[10],"The":[11,73],"notion":[12],"membership-mapping":[14],"is":[15,52],"developed":[16],"using":[17,109],"measure":[18],"theory":[19],"basis":[20],"to":[21,37,89,116],"learn":[22],"data":[23],"representation":[24],"via":[25],"a":[26,47,76,84,91],"fuzzy":[27],"membership":[28],"function.":[29],"An":[30],"alternative":[31],"conception":[32],"deep":[34],"autoencoder,":[35],"referred":[36],"as":[38],"Conditionally":[39],"Deep":[40],"Membership-Mapping":[41],"Autoencoder":[42],"(CDMMA)":[43],"(that":[44],"consists":[45],"nested":[48],"compositions":[49],"membership-mappings),":[51],"considered.":[53],"Under":[54],"practice-oriented":[55],"settings,":[56],"an":[57],"analytical":[58],"solution":[59],"for":[60],"learning":[62,78],"CDMFA":[64],"can":[65],"be":[66],"derived":[67],"by":[68],"means":[69],"variational":[71],"optimization.":[72],"proposes":[75],"approach":[79],"that":[80],"combines":[81],"CDMMA":[82],"with":[83,97],"tailored":[85],"noise":[86],"adding":[87],"mechanism":[88],"achieve":[90],"given":[92],"level":[93],"privacy-loss":[95],"bound":[96],"minimum":[99],"perturbation":[100],"data.":[103],"Numerous":[104],"experiments":[105],"were":[106],"carried":[107],"out":[108],"MNIST,":[110],"USPS,":[111],"Office,":[112],"and":[113],"Caltech256":[114],"datasets":[115],"verify":[117],"competitive":[119],"robust":[120],"performance":[121],"proposed":[124],"methodology.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2021-05-24T00:00:00"}