{"date_created":"2023-08-22T14:20:18Z","oa_version":"Preprint","date_published":"2023-04-12T00:00:00Z","title":"Causal triplet: An open challenge for intervention-centric causal representation learning","citation":{"short":"Y. Liu, A. Alahi, C. Russell, M. Horn, D. Zietlow, B. Schölkopf, F. Locatello, in:, 2nd Conference on Causal Learning and Reasoning, 2023.","ama":"Liu Y, Alahi A, Russell C, et al. Causal triplet: An open challenge for intervention-centric causal representation learning. In: 2nd Conference on Causal Learning and Reasoning. ; 2023.","chicago":"Liu, Yuejiang, Alexandre Alahi, Chris Russell, Max Horn, Dominik Zietlow, Bernhard Schölkopf, and Francesco Locatello. “Causal Triplet: An Open Challenge for Intervention-Centric Causal Representation Learning.” In 2nd Conference on Causal Learning and Reasoning, 2023.","mla":"Liu, Yuejiang, et al. “Causal Triplet: An Open Challenge for Intervention-Centric Causal Representation Learning.” 2nd Conference on Causal Learning and Reasoning, 2023.","apa":"Liu, Y., Alahi, A., Russell, C., Horn, M., Zietlow, D., Schölkopf, B., & Locatello, F. (2023). Causal triplet: An open challenge for intervention-centric causal representation learning. In 2nd Conference on Causal Learning and Reasoning. Tübingen, Germany.","ista":"Liu Y, Alahi A, Russell C, Horn M, Zietlow D, Schölkopf B, Locatello F. 2023. Causal triplet: An open challenge for intervention-centric causal representation learning. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning.","ieee":"Y. Liu et al., “Causal triplet: An open challenge for intervention-centric causal representation learning,” in 2nd Conference on Causal Learning and Reasoning, Tübingen, Germany, 2023."},"author":[{"first_name":"Yuejiang","last_name":"Liu","full_name":"Liu, Yuejiang"},{"full_name":"Alahi, Alexandre","first_name":"Alexandre","last_name":"Alahi"},{"last_name":"Russell","first_name":"Chris","full_name":"Russell, Chris"},{"full_name":"Horn, Max","first_name":"Max","last_name":"Horn"},{"last_name":"Zietlow","first_name":"Dominik","full_name":"Zietlow, Dominik"},{"full_name":"Schölkopf, Bernhard","last_name":"Schölkopf","first_name":"Bernhard"},{"orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco"}],"external_id":{"arxiv":["2301.05169"]},"month":"04","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"text":"Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In this paper, we present Causal Triplet, a causal representation learning benchmark featuring not only visually more complex scenes, but also two crucial desiderata commonly overlooked in previous works: (i) an actionable counterfactual setting, where only certain object-level variables allow for counterfactual observations whereas others do not; (ii) an interventional downstream task with an emphasis on out-of-distribution robustness from the independent causal mechanisms principle. Through extensive experiments, we find that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts. However, recent causal representation learning methods still struggle to identify such latent structures, indicating substantial challenges and opportunities for future work.","lang":"eng"}],"publication_status":"published","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2301.05169","open_access":"1"}],"quality_controlled":"1","_id":"14214","year":"2023","language":[{"iso":"eng"}],"extern":"1","date_updated":"2023-09-13T09:23:08Z","status":"public","day":"12","article_processing_charge":"No","publication":"2nd Conference on Causal Learning and Reasoning","type":"conference","conference":{"end_date":"2023-04-14","start_date":"2023-04-11","name":"CLeaR: Conference on Causal Learning and Reasoning","location":"Tübingen, Germany"},"department":[{"_id":"FrLo"}]}