{"title":"Are disentangled representations helpful for abstract visual reasoning?","month":"05","external_id":{"arxiv":["1905.12506"]},"publication_identifier":{"isbn":["9781713807933"]},"_id":"14193","citation":{"ieee":"S. van Steenkiste, F. Locatello, J. Schmidhuber, and O. Bachem, “Are disentangled representations helpful for abstract visual reasoning?,” in <i>Advances in Neural Information Processing Systems</i>, Vancouver, Canada, 2019, vol. 32.","chicago":"Steenkiste, Sjoerd van, Francesco Locatello, Jürgen Schmidhuber, and Olivier Bachem. “Are Disentangled Representations Helpful for Abstract Visual Reasoning?” In <i>Advances in Neural Information Processing Systems</i>, Vol. 32, 2019.","mla":"Steenkiste, Sjoerd van, et al. “Are Disentangled Representations Helpful for Abstract Visual Reasoning?” <i>Advances in Neural Information Processing Systems</i>, vol. 32, 2019.","ista":"Steenkiste S van, Locatello F, Schmidhuber J, Bachem O. 2019. Are disentangled representations helpful for abstract visual reasoning? Advances in Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems vol. 32.","ama":"Steenkiste S van, Locatello F, Schmidhuber J, Bachem O. Are disentangled representations helpful for abstract visual reasoning? In: <i>Advances in Neural Information Processing Systems</i>. Vol 32. ; 2019.","apa":"Steenkiste, S. van, Locatello, F., Schmidhuber, J., &#38; Bachem, O. (2019). Are disentangled representations helpful for abstract visual reasoning? In <i>Advances in Neural Information Processing Systems</i> (Vol. 32). Vancouver, Canada.","short":"S. van Steenkiste, F. Locatello, J. Schmidhuber, O. Bachem, in:, Advances in Neural Information Processing Systems, 2019."},"type":"conference","oa_version":"Preprint","oa":1,"publication_status":"published","conference":{"name":"NeurIPS: Neural Information Processing Systems","end_date":"2019-12-14","location":"Vancouver, Canada","start_date":"2019-12-08"},"volume":32,"author":[{"full_name":"Steenkiste, Sjoerd van","first_name":"Sjoerd van","last_name":"Steenkiste"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello","full_name":"Locatello, Francesco","first_name":"Francesco","orcid":"0000-0002-4850-0683"},{"last_name":"Schmidhuber","full_name":"Schmidhuber, Jürgen","first_name":"Jürgen"},{"last_name":"Bachem","full_name":"Bachem, Olivier","first_name":"Olivier"}],"extern":"1","language":[{"iso":"eng"}],"department":[{"_id":"FrLo"}],"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.1905.12506","open_access":"1"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"text":"A disentangled representation encodes information about the salient factors\r\nof variation in the data independently. Although it is often argued that this\r\nrepresentational format is useful in learning to solve many real-world\r\ndown-stream tasks, there is little empirical evidence that supports this claim.\r\nIn this paper, we conduct a large-scale study that investigates whether\r\ndisentangled representations are more suitable for abstract reasoning tasks.\r\nUsing two new tasks similar to Raven's Progressive Matrices, we evaluate the\r\nusefulness of the representations learned by 360 state-of-the-art unsupervised\r\ndisentanglement models. Based on these representations, we train 3600 abstract\r\nreasoning models and observe that disentangled representations do in fact lead\r\nto better down-stream performance. In particular, they enable quicker learning\r\nusing fewer samples.","lang":"eng"}],"status":"public","date_created":"2023-08-22T14:09:53Z","date_updated":"2023-09-12T09:02:43Z","intvolume":"        32","publication":"Advances in Neural Information Processing Systems","date_published":"2019-05-29T00:00:00Z","quality_controlled":"1","article_processing_charge":"No","day":"29","year":"2019"}