{"id":"https://openalex.org/W3043229062","doi":"https://doi.org/10.1109/jiot.2020.3009358","title":"Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence","display_name":"Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence","publication_year":2020,"publication_date":"2020-07-15","ids":{"openalex":"https://openalex.org/W3043229062","doi":"https://doi.org/10.1109/jiot.2020.3009358","mag":"3043229062"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2020.3009358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.3009358","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.13018","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aaqib Saeed","orcid":"https://orcid.org/0000-0003-1473-0322"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aaqib Saeed","raw_affiliation_strings":["Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, AE, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1473-0322","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, AE, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Flora D. Salim","orcid":"https://orcid.org/0000-0002-1237-1664"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Flora D. Salim","raw_affiliation_strings":["School of Science and RMIT Centre for Information Discovery and Data Analytics, RMIT University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1237-1664","affiliations":[{"raw_affiliation_string":"School of Science and RMIT Centre for Information Discovery and Data Analytics, RMIT University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tanir Ozcelebi","orcid":"https://orcid.org/0000-0001-7092-5998"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tanir Ozcelebi","raw_affiliation_strings":["Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, AE, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-7092-5998","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, AE, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":null,"display_name":"Johan Lukkien","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Johan Lukkien","raw_affiliation_strings":["Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, AE, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, AE, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9781,"has_fulltext":true,"cited_by_count":104,"citation_normalized_percentile":{"value":0.94931432,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"8","issue":"2","first_page":"1030","last_page":"1040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11196","display_name":"Non-Invasive Vital Sign Monitoring","score":0.1168999969959259,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11196","display_name":"Non-Invasive Vital Sign Monitoring","score":0.1168999969959259,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.09309999644756317,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.0917000025510788,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5795000195503235},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5791000127792358},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5730999708175659},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5365999937057495},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4999000132083893},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4253000020980835},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4122999906539917},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3862999975681305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8826000094413757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6725000143051147},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5724999904632568},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4253000020980835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/jiot.2020.3009358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.3009358","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2007.13018","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.13018","pdf_url":"https://arxiv.org/pdf/2007.13018","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,"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":null,"raw_type":"text"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/227755e3-cadb-434f-adc1-2a545078ff84","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/227755e3-cadb-434f-adc1-2a545078ff84","pdf_url":"https://pure.tue.nl/ws/files/166745422/2007.13018v1.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Saeed, A, Salim, F D, Ozcelebi, T & Lukkien, J 2021, 'Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence', IEEE Internet of Things Journal, vol. 8, no. 2, 9141293, pp. 1030-1040. https://doi.org/10.1109/JIOT.2020.3009358","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:alma61RMIT.INST:11271270380001341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/JIOT.2020.3009358","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:pure.tue.nl:publications/227755e3-cadb-434f-adc1-2a545078ff84","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85099155931&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Saeed, A, Salim, F D, Ozcelebi, T & Lukkien, J 2021, 'Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence', IEEE Internet of Things Journal, vol. 8, no. 2, 9141293, pp. 1030-1040. https://doi.org/10.1109/JIOT.2020.3009358","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:tue:oai:pure.tue.nl:publications/227755e3-cadb-434f-adc1-2a545078ff84","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/227755e3-cadb-434f-adc1-2a545078ff84","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Internet of Things Journal, 8(2):9141293, 1030 - 1040. Institute of Electrical and Electronics Engineers","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.13018","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.13018","pdf_url":"https://arxiv.org/pdf/2007.13018","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,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5421811537","display_name":"Secure COnnected Trustable Things","funder_award_id":"737422","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1996021349","https://openalex.org/W2004255221","https://openalex.org/W2025768430","https://openalex.org/W2057907879","https://openalex.org/W2078831169","https://openalex.org/W2103184652","https://openalex.org/W2113896236","https://openalex.org/W2144691514","https://openalex.org/W2157364932","https://openalex.org/W2162800060","https://openalex.org/W2173213060","https://openalex.org/W2321533354","https://openalex.org/W2387306914","https://openalex.org/W2558661413","https://openalex.org/W2569173133","https://openalex.org/W2599837529","https://openalex.org/W2604096629","https://openalex.org/W2619383789","https://openalex.org/W2736191430","https://openalex.org/W2763219399","https://openalex.org/W2767079719","https://openalex.org/W2769112066","https://openalex.org/W2777460464","https://openalex.org/W2894771803","https://openalex.org/W2896422817","https://openalex.org/W2919115771","https://openalex.org/W2962960500","https://openalex.org/W2963486369","https://openalex.org/W2963863119","https://openalex.org/W3010852232","https://openalex.org/W3014208382","https://openalex.org/W3099025572","https://openalex.org/W4236853429","https://openalex.org/W6607775107","https://openalex.org/W6630709637","https://openalex.org/W6638803421","https://openalex.org/W6678941442","https://openalex.org/W6682691769","https://openalex.org/W6728757088","https://openalex.org/W6738383168","https://openalex.org/W6748098738","https://openalex.org/W6775625563"],"related_works":[],"abstract_inverted_index":{"Smartphones,":[0],"wearables,":[1],"and":[2,28,102,124,195,206,218],"Internet-of-Things":[3],"(IoT)":[4],"devices":[5],"produce":[6],"a":[7,16,37,76,110,118,122,129,140,183,227],"wealth":[8],"of":[9,32,52,121,148,170,235],"data":[10,57,158,237],"that":[11],"cannot":[12,63],"be":[13,64],"accumulated":[14],"in":[15,163,190,215,226],"centralized":[17],"repository":[18],"for":[19,40],"learning":[20,35,41,82],"supervised":[21,204],"models":[22,42],"due":[23],"to":[24,88,115],"privacy,":[25],"bandwidth":[26],"limitations,":[27],"the":[29,50,146,168,224,233],"prohibitive":[30],"cost":[31],"annotations.":[33],"Federated":[34],"provides":[36],"compelling":[38],"framework":[39],"from":[43,92,173],"decentralized":[44],"data,":[45],"but":[46],"conventionally,":[47],"it":[48,207,222,231],"assumes":[49],"availability":[51],"labeled":[53,236],"samples,":[54],"whereas":[55],"on-device":[56],"are":[58],"generally":[59],"either":[60],"unlabeled":[61,93,175],"or":[62],"annotated":[65],"readily":[66],"through":[67,239],"user":[68],"interaction.":[69],"To":[70],"address":[71],"these":[72],"issues,":[73],"we":[74],"propose":[75],"self-supervised":[77,241],"approach":[78],"termed":[79],"scalogram-signal":[80],"correspondence":[81],"based":[83],"on":[84,155,178],"wavelet":[85],"transform":[86],"(WT)":[87],"learn":[89],"useful":[90],"representations":[91,171],"sensor":[94],"inputs":[95],"as":[96,230],"electroencephalography,":[97],"blood":[98],"volume":[99,234],"pulse,":[100],"accelerometer,":[101],"WiFi":[103],"channel-state":[104],"information.":[105],"Our":[106,197],"auxiliary":[107],"task":[108],"requires":[109],"deep":[111],"temporal":[112],"neural":[113],"network":[114],"determine":[116],"if":[117],"given":[119],"pair":[120],"signal":[123],"its":[125],"complementary":[126],"view":[127],"(i.e.,":[128],"scalogram":[130],"generated":[131],"with":[132,135,151,181,202,213],"WT)":[133],"align":[134],"each":[136],"other,":[137],"by":[138],"optimizing":[139],"contrastive":[141],"objective.":[142],"We":[143,166],"extensively":[144],"assess":[145],"quality":[147],"learned":[149,172],"features":[150],"our":[152],"multiview":[153],"strategy":[154],"diverse":[156],"public":[157],"sets,":[159],"achieving":[160],"strong":[161],"performance":[162,201],"all":[164],"domains.":[165],"demonstrate":[167],"effectiveness":[169],"an":[174],"input":[176],"collection":[177],"downstream":[179],"tasks":[180],"training":[182],"linear":[184],"classifier":[185],"over":[186],"pretrained":[187],"network,":[188],"usefulness":[189],"low-data":[191],"regime,":[192],"transfer":[193],"learning,":[194],"cross-validation.":[196],"methodology":[198],"achieves":[199],"competitive":[200],"fully":[203],"networks":[205],"works":[208],"significantly":[209],"better":[210],"than":[211],"pretraining":[212],"autoencoders":[214],"both":[216],"central":[217],"federated":[219],"contexts.":[220],"Notably,":[221],"improves":[223],"generalization":[225],"semisupervised":[228],"setting":[229],"reduces":[232],"required":[238],"leveraging":[240],"learning.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-07-23T00:00:00"}