{"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/infocatvae-representation-learning-with","title":"InfoCatVAE: Representation Learning with Categorical Variational Autoencoders","arxiv_id":"1806.08240","date":"2018-06-20","proceeding":null,"authors":["Edouard Pineau","Marc Lelarge"],"abstract":"This paper describes InfoCatVAE, an extension of the variational autoencoder\nthat enables unsupervised disentangled representation learning. InfoCatVAE uses\nmultimodal distributions for the prior and the inference network and then\nmaximizes the evidence lower bound objective (ELBO). We connect the new ELBO\nderived for our model with a natural soft clustering objective which explains\nthe robustness of our approach. We then adapt the InfoGANs method to our\nsetting in order to maximize the mutual information between the categorical\ncode and the generated inputs and obtain an improved model.","url_abs":"http://arxiv.org/abs/1806.08240v2","url_pdf":"http://arxiv.org/pdf/1806.08240v2.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":"infocatvae-representation-learning-with","repo_url":"https://github.com/edouardpineau/infoCatVAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}