@article{
 title = {Isolating Sources of Disentanglement in Variational Autoencoders},
 type = {article},
 year = {2018},
 websites = {https://arxiv.org/abs/1802.04942v5},
 month = {2},
 id = {cadbac75-f2d0-3482-a13f-e5a01928323c},
 created = {2022-03-28T09:45:01.766Z},
 accessed = {2022-02-22},
 file_attached = {true},
 profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
 group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
 last_modified = {2022-03-29T08:02:29.234Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {chenIsolatingSourcesDisentanglement2018},
 source_type = {article},
 private_publication = {false},
 abstract = {We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our \$\textbackslashbeta\$-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art \$\textbackslashbeta\$-VAE objective for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the latent variables model is trained using our framework.},
 bibtype = {article},
 author = {Chen, Ricky T Q and Li, Xuechen and Grosse, Roger and Duvenaud, David}
}

{"_id":"yLEoDLN4AvJgJxMLe","bibbaseid":"chen-li-grosse-duvenaud-isolatingsourcesofdisentanglementinvariationalautoencoders-2018","downloads":2,"creationDate":"2018-09-18T19:03:55.794Z","title":"Isolating Sources of Disentanglement in Variational Autoencoders","author_short":["Chen, R., T., Q.","Li, X.","Grosse, R.","Duvenaud, D."],"year":2018,"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibdata":{"title":"Isolating Sources of Disentanglement in Variational Autoencoders","type":"article","year":"2018","websites":"https://arxiv.org/abs/1802.04942v5","month":"2","id":"cadbac75-f2d0-3482-a13f-e5a01928323c","created":"2022-03-28T09:45:01.766Z","accessed":"2022-02-22","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-03-29T08:02:29.234Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"chenIsolatingSourcesDisentanglement2018","source_type":"article","private_publication":false,"abstract":"We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our \\$\\textbackslashbeta\\$-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art \\$\\textbackslashbeta\\$-VAE objective for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the latent variables model is trained using our framework.","bibtype":"article","author":"Chen, Ricky T Q and Li, Xuechen and Grosse, Roger and Duvenaud, David","bibtex":"@article{\n title = {Isolating Sources of Disentanglement in Variational Autoencoders},\n type = {article},\n year = {2018},\n websites = {https://arxiv.org/abs/1802.04942v5},\n month = {2},\n id = {cadbac75-f2d0-3482-a13f-e5a01928323c},\n created = {2022-03-28T09:45:01.766Z},\n accessed = {2022-02-22},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-03-29T08:02:29.234Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {chenIsolatingSourcesDisentanglement2018},\n source_type = {article},\n private_publication = {false},\n abstract = {We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our \\$\\textbackslashbeta\\$-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art \\$\\textbackslashbeta\\$-VAE objective for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the latent variables model is trained using our framework.},\n bibtype = {article},\n author = {Chen, Ricky T Q and Li, Xuechen and Grosse, Roger and Duvenaud, David}\n}","author_short":["Chen, R., T., Q.","Li, X.","Grosse, R.","Duvenaud, D."],"urls":{"Website":"https://arxiv.org/abs/1802.04942v5"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"chen-li-grosse-duvenaud-isolatingsourcesofdisentanglementinvariationalautoencoders-2018","role":"author","metadata":{"authorlinks":{"chen, t":"https://learning.cs.toronto.edu/publications.html"}},"downloads":2},"search_terms":["isolating","sources","disentanglement","variational","autoencoders","chen","li","grosse","duvenaud"],"keywords":[],"authorIDs":["5ba14c1bdfa20f100000004c","yZEWbJhYipxiQYJCh"],"dataSources":["vy4JCDJboyp63rw8W","ya2CyA73rpZseyrZ8"]}