{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/variational-inference-of-disentangled-latent","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","arxiv_id":"1711.00848","date":"2017-11-02","proceeding":"ICLR 2018 1","authors":["Abhishek Kumar","Prasanna Sattigeri","Avinash Balakrishnan"],"abstract":"Disentangled representations, where the higher level data generative factors\nare reflected in disjoint latent dimensions, offer several benefits such as\nease of deriving invariant representations, transferability to other tasks,\ninterpretability, etc. We consider the problem of unsupervised learning of\ndisentangled representations from large pool of unlabeled observations, and\npropose a variational inference based approach to infer disentangled latent\nfactors. We introduce a regularizer on the expectation of the approximate\nposterior over observed data that encourages the disentanglement. We also\npropose a new disentanglement metric which is better aligned with the\nqualitative disentanglement observed in the decoder's output. We empirically\nobserve significant improvement over existing methods in terms of both\ndisentanglement and data likelihood (reconstruction quality).","url_abs":"http://arxiv.org/abs/1711.00848v3","url_pdf":"http://arxiv.org/pdf/1711.00848v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"variational-inference-of-disentangled-latent","repo_url":"https://github.com/carbonati/variational-zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"variational-inference-of-disentangled-latent","repo_url":"https://github.com/facebookresearch/disentangling-correlated-factors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.00848","atlas_url":"https://app.syntology.ai/?focus=1711.00848","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}