{"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/challenging-common-assumptions-in-the-1","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","arxiv_id":null,"date":"2019-03-06","proceeding":"ICLR Workshop RML 2019 5","authors":["Anonymous"],"abstract":"The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms.\nIn this paper, we provide a sober look on recent progress in the field and challenge some common assumptions.\nWe train more than 12000 models covering most prominent methods and evaluation metrics in a reproducible large-scale experimental study on seven different data sets.\nWe observe that while the different methods successfully enforce properties ``encouraged'' by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision.\nFurthermore, increased disentanglement does not seem to lead to a decreased sample complexity of learning for downstream tasks. \nOur results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision, investigate concrete benefits of enforcing disentanglement of the learned representations, and consider a reproducible experimental setup covering several data sets.","url_abs":"https://openreview.net/forum?id=Byg6VhUp8V","url_pdf":"https://openreview.net/pdf?id=Byg6VhUp8V","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":"challenging-common-assumptions-in-the-1","repo_url":"https://github.com/google-research/disentanglement_lib","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}