Semi-supervised learning with deep generative models. Kingma, D., P., Rezende, D., J., Mohamed, S., & Welling, M. Advances in Neural Information Processing Systems, 4(January):3581-3589, 2014.
![Semi-supervised learning with deep generative models [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones. Generative approaches have thus far been either inflexible, inefficient or non-scalable. We show that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.
@article{
title = {Semi-supervised learning with deep generative models},
type = {article},
year = {2014},
pages = {3581-3589},
volume = {4},
id = {7863cc34-980a-36aa-8ed2-f13a21e537d3},
created = {2021-09-09T14:35:21.228Z},
file_attached = {true},
profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
last_modified = {2022-03-28T09:45:09.375Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Kingma2014},
folder_uuids = {1853f94b-7af1-40fa-b068-4758e9a02bc4},
private_publication = {false},
abstract = {The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones. Generative approaches have thus far been either inflexible, inefficient or non-scalable. We show that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.},
bibtype = {article},
author = {Kingma, Diederik P. and Rezende, Danilo J. and Mohamed, Shakir and Welling, Max},
journal = {Advances in Neural Information Processing Systems},
number = {January}
}Downloads: 0
{"_id":"P37f3H57WgtYuvHwH","bibbaseid":"kingma-rezende-mohamed-welling-semisupervisedlearningwithdeepgenerativemodels-2014","author_short":["Kingma, D., P.","Rezende, D., J.","Mohamed, S.","Welling, M."],"bibdata":{"title":"Semi-supervised learning with deep generative models","type":"article","year":"2014","pages":"3581-3589","volume":"4","id":"7863cc34-980a-36aa-8ed2-f13a21e537d3","created":"2021-09-09T14:35:21.228Z","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-03-28T09:45:09.375Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Kingma2014","folder_uuids":"1853f94b-7af1-40fa-b068-4758e9a02bc4","private_publication":false,"abstract":"The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones. Generative approaches have thus far been either inflexible, inefficient or non-scalable. We show that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.","bibtype":"article","author":"Kingma, Diederik P. and Rezende, Danilo J. and Mohamed, Shakir and Welling, Max","journal":"Advances in Neural Information Processing Systems","number":"January","bibtex":"@article{\n title = {Semi-supervised learning with deep generative models},\n type = {article},\n year = {2014},\n pages = {3581-3589},\n volume = {4},\n id = {7863cc34-980a-36aa-8ed2-f13a21e537d3},\n created = {2021-09-09T14:35:21.228Z},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-03-28T09:45:09.375Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Kingma2014},\n folder_uuids = {1853f94b-7af1-40fa-b068-4758e9a02bc4},\n private_publication = {false},\n abstract = {The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones. Generative approaches have thus far been either inflexible, inefficient or non-scalable. We show that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.},\n bibtype = {article},\n author = {Kingma, Diederik P. and Rezende, Danilo J. and Mohamed, Shakir and Welling, Max},\n journal = {Advances in Neural Information Processing Systems},\n number = {January}\n}","author_short":["Kingma, D., P.","Rezende, D., J.","Mohamed, S.","Welling, M."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/25179fe1-b216-4613-0613-9baf656864c2/14065298.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"kingma-rezende-mohamed-welling-semisupervisedlearningwithdeepgenerativemodels-2014","role":"author","metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["5jEuhQhgRx3py8LmG","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["semi","supervised","learning","deep","generative","models","kingma","rezende","mohamed","welling"],"title":"Semi-supervised learning with deep generative models","year":2014}