{"day":"01","status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","OA_type":"gold","publication_status":"published","tmp":{"short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"external_id":{"arxiv":["2409.02772"]},"corr_author":"1","conference":{"end_date":"2024-12-16","start_date":"2024-12-16","name":"NeurIPS: Neural Information Processing Systems","location":"Vancouver, Canada"},"acknowledgement":"We thank Jiaqi Zhang, Francesco Montagna, David Lopez-Paz, Kartik Ahuja, Thomas Kipf, Sara\r\nMagliacane, Julius von Kügelgen, Kun Zhang, and Bernhard Schölkopf for extremely helpful discussion. Riccardo Cadei was supported by a Google Research Scholar Award to Francesco Locatello. We acknowledge the Third Bellairs Workshop on Causal Representation Learning held at the Bellairs Research Institute, February 9/16, 2024, and a debate on the difference between interventions and counterfactuals in disentanglement and CRL that took place during Dhanya Sridhar’s lecture, which motivated us to significantly broaden the scope of the paper. We thank Dhanya and all participants of the workshop.","abstract":[{"text":"Causal representation learning aims at recovering latent causal variables from high-dimensional observations to solve causal downstream tasks, such as predicting the effect of new interventions or more robust classification. A plethora of methods have been developed, each tackling carefully crafted problem settings that lead to different types of identifiability. The folklore is that these different settings are important, as they are often linked to different rungs of Pearl's causal hierarchy, although not all neatly fit. Our main contribution is to show that many existing causal representation learning approaches methodologically align the representation to known data symmetries. Identification of the variables is guided by equivalence classes across different \"data pockets\" that are not necessarily causal. This result suggests important implications, allowing us to unify many existing approaches in a single method that can mix and match different assumptions, including non-causal ones, based on the invariances relevant to our application. It also significantly benefits applicability, which we demonstrate by improving treatment effect estimation on real-world high-dimensional ecological data. Overall, this paper clarifies the role of causality assumptions in the discovery of causal variables and shifts the focus to preserving data symmetries.","lang":"eng"}],"publication":"38th Conference on Neural Information Processing Systems","publisher":"Curran Associates","arxiv":1,"citation":{"ista":"Yao D, Rancati D, Cadei R, Fumero M, Locatello F. 2024. Unifying causal representation learning with the invariance principle. 38th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, NeurIPS, vol. 38.","ama":"Yao D, Rancati D, Cadei R, Fumero M, Locatello F. Unifying causal representation learning with the invariance principle. In: <i>38th Conference on Neural Information Processing Systems</i>. Vol 38. Curran Associates; 2024.","ieee":"D. Yao, D. Rancati, R. Cadei, M. Fumero, and F. Locatello, “Unifying causal representation learning with the invariance principle,” in <i>38th Conference on Neural Information Processing Systems</i>, Vancouver, Canada, 2024, vol. 38.","chicago":"Yao, Dingling, Dario Rancati, Riccardo Cadei, Marco Fumero, and Francesco Locatello. “Unifying Causal Representation Learning with the Invariance Principle.” In <i>38th Conference on Neural Information Processing Systems</i>, Vol. 38. Curran Associates, 2024.","short":"D. Yao, D. Rancati, R. Cadei, M. Fumero, F. Locatello, in:, 38th Conference on Neural Information Processing Systems, Curran Associates, 2024.","mla":"Yao, Dingling, et al. “Unifying Causal Representation Learning with the Invariance Principle.” <i>38th Conference on Neural Information Processing Systems</i>, vol. 38, Curran Associates, 2024.","apa":"Yao, D., Rancati, D., Cadei, R., Fumero, M., &#38; Locatello, F. (2024). Unifying causal representation learning with the invariance principle. In <i>38th Conference on Neural Information Processing Systems</i> (Vol. 38). Vancouver, Canada: Curran Associates."},"volume":38,"has_accepted_license":"1","file":[{"file_size":800035,"relation":"main_file","checksum":"9b78ce3f8cb5b0855e34cc5a7f99ef08","date_updated":"2025-02-05T09:23:06Z","date_created":"2025-02-05T09:23:06Z","access_level":"open_access","content_type":"application/pdf","creator":"dernst","success":1,"file_id":"19011","file_name":"2024_NeurIPS_Yao2.pdf"}],"title":"Unifying causal representation learning with the invariance principle","quality_controlled":"1","date_updated":"2025-02-05T09:24:02Z","year":"2024","month":"12","file_date_updated":"2025-02-05T09:23:06Z","article_processing_charge":"No","language":[{"iso":"eng"}],"oa":1,"department":[{"_id":"FrLo"}],"date_created":"2025-02-05T09:23:25Z","alternative_title":["NeurIPS"],"author":[{"first_name":"Dingling","last_name":"Yao","full_name":"Yao, Dingling","id":"d3e02e50-48a8-11ee-8f62-c108061797fa"},{"full_name":"Rancati, Dario","id":"feb58f2e-72ef-11ef-b75a-8f0894539cd0","first_name":"Dario","last_name":"Rancati"},{"last_name":"Cadei","first_name":"Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","full_name":"Cadei, Riccardo"},{"last_name":"Fumero","first_name":"Marco","id":"1c1593eb-393f-11ef-bb8e-ab4f1e979650","full_name":"Fumero, Marco"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","last_name":"Locatello","first_name":"Francesco","orcid":"0000-0002-4850-0683"}],"OA_place":"publisher","oa_version":"Published Version","ddc":["000"],"_id":"19010","intvolume":"        38","type":"conference","date_published":"2024-12-01T00:00:00Z"}