[{"project":[{"name":"IST-BRIDGE: International postdoctoral program","grant_number":"101034413","call_identifier":"H2020","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c"},{"grant_number":"COE12","name":"Bilateral Artificial Intelligence (Locatello)","_id":"a392d8f0-b034-11f1-b88e-d3025c6734f6"}],"day":"01","scopus_import":"1","alternative_title":["PMLR"],"volume":267,"abstract":[{"lang":"eng","text":"We present Mechanistic PDE Networks -- a model for discovery of governing partial differential equations from data. Mechanistic PDE Networks represent spatiotemporal data as space-time dependent linear partial differential equations in neural network hidden representations. The represented PDEs are then solved and decoded for specific tasks. The learned PDE representations naturally express the spatiotemporal dynamics in data in neural network hidden space, enabling increased modeling power. Solving the PDE representations in a compute and memory-efficient way, however, is a significant challenge. We develop a native, GPU-capable, parallel, sparse and differentiable multigrid solver specialized for linear partial differential equations that acts as a module in Mechanistic PDE Networks. Leveraging the PDE solver we propose a discovery architecture that can discovers nonlinear PDEs in complex settings, while being robust to noise. We validate PDE discovery on a number of PDEs including reaction-diffusion and Navier-Stokes equations."}],"ec_funded":1,"page":"48962-48973","ddc":["000"],"publication":"42nd International Conference on Machine Learning","tmp":{"short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png"},"oa_version":"Published Version","acknowledgement":"AP. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 101034413.\r\nFL. This research was funded in whole or in part by the Austrian Science Fund (FWF) 10.55776/COE12. For open access purposes, the author has applied a CC BY public\r\ncopyright license to any author accepted manuscript version arising from this submission.","language":[{"iso":"eng"}],"file_date_updated":"2025-12-16T12:21:49Z","file":[{"content_type":"application/pdf","file_name":"2025_ICML_Pervez.pdf","checksum":"933cb673fb41416f537278fb990df6c3","date_created":"2025-12-16T12:21:49Z","file_size":993381,"file_id":"20827","relation":"main_file","creator":"dernst","access_level":"open_access","success":1,"date_updated":"2025-12-16T12:21:49Z"}],"publication_identifier":{"eissn":["2640-3498"]},"citation":{"apa":"Pervez, A. A., Gavves, E., &#38; Locatello, F. (2025). Mechanistic PDE networks for discovery of governing equations. In <i>42nd International Conference on Machine Learning</i> (Vol. 267, pp. 48962–48973). Vancouver, Canada: ML Research Press.","short":"A.A. Pervez, E. Gavves, F. Locatello, in:, 42nd International Conference on Machine Learning, ML Research Press, 2025, pp. 48962–48973.","chicago":"Pervez, Adeel A, Efstratios Gavves, and Francesco Locatello. “Mechanistic PDE Networks for Discovery of Governing Equations.” In <i>42nd International Conference on Machine Learning</i>, 267:48962–73. ML Research Press, 2025.","ieee":"A. A. Pervez, E. Gavves, and F. Locatello, “Mechanistic PDE networks for discovery of governing equations,” in <i>42nd International Conference on Machine Learning</i>, Vancouver, Canada, 2025, vol. 267, pp. 48962–48973.","ama":"Pervez AA, Gavves E, Locatello F. Mechanistic PDE networks for discovery of governing equations. In: <i>42nd International Conference on Machine Learning</i>. Vol 267. ML Research Press; 2025:48962-48973.","ista":"Pervez AA, Gavves E, Locatello F. 2025. Mechanistic PDE networks for discovery of governing equations. 42nd International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 267, 48962–48973.","mla":"Pervez, Adeel A., et al. “Mechanistic PDE Networks for Discovery of Governing Equations.” <i>42nd International Conference on Machine Learning</i>, vol. 267, ML Research Press, 2025, pp. 48962–73."},"_id":"20817","status":"public","has_accepted_license":"1","quality_controlled":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2026-09-16T07:17:18Z","year":"2025","title":"Mechanistic PDE networks for discovery of governing equations","corr_author":"1","oa":1,"author":[{"first_name":"Adeel A","id":"fca6d90c-d47f-11ee-bc87-93ff51604981","last_name":"Pervez","full_name":"Pervez, Adeel A"},{"last_name":"Gavves","full_name":"Gavves, Efstratios","first_name":"Efstratios"},{"last_name":"Locatello","full_name":"Locatello, Francesco","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","orcid":"0000-0002-4850-0683"}],"publisher":"ML Research Press","intvolume":"       267","related_material":{"link":[{"url":"https://github.com/ alpz/mech-nn-discovery-pde","relation":"software"}]},"arxiv":1,"date_published":"2025-05-01T00:00:00Z","type":"conference","publication_status":"published","department":[{"_id":"FrLo"}],"OA_type":"gold","month":"05","OA_place":"publisher","article_processing_charge":"No","external_id":{"arxiv":["2502.18377"]},"conference":{"start_date":"2025-07-13","location":"Vancouver, Canada","end_date":"2025-07-19","name":"ICML: International Conference on Machine Learning"},"date_created":"2025-12-14T23:02:04Z"},{"oa":1,"author":[{"id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","first_name":"Riccardo","last_name":"Cadei","full_name":"Cadei, Riccardo"},{"full_name":"Demirel, Ilker","last_name":"Demirel","first_name":"Ilker"},{"first_name":"Piersilvio","full_name":"De Bartolomeis, Piersilvio","last_name":"De Bartolomeis"},{"full_name":"Lindorfer, Lukas","last_name":"Lindorfer","first_name":"Lukas","id":"85f0e6d3-06b3-11ec-8982-8c5049fa4455"},{"orcid":"0000-0002-2193-3868","first_name":"Sylvia","id":"2F64EC8C-F248-11E8-B48F-1D18A9856A87","full_name":"Cremer, Sylvia","last_name":"Cremer"},{"first_name":"Cordelia","last_name":"Schmid","full_name":"Schmid, Cordelia"},{"orcid":"0000-0002-4850-0683","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","full_name":"Locatello, Francesco","last_name":"Locatello"}],"corr_author":"1","intvolume":"        38","publisher":"Neural Information Processing Systems Foundation","_id":"22832","quality_controlled":"1","status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"Prediction-Powered Causal Inferences","year":"2025","date_updated":"2026-09-17T06:56:40Z","doi":"10.52202/085713-2479","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2502.06343","open_access":"1"}],"publication_status":"published","article_processing_charge":"No","month":"12","OA_place":"repository","OA_type":"green","department":[{"_id":"FrLo"},{"_id":"GradSch"},{"_id":"SyCr"}],"conference":{"end_date":"2025-12-07","name":"NeurIPS: Neural Information Processing Systems","start_date":"2025-12-02","location":"San Diego, CA, United States"},"dataavailabilitystatement":"We share all the code implementation in the supplementary material.\r\nOur new experimental ecology dataset preview is anonymously shared on Figshare at\r\nhttps://figshare.com/s/9a490b6f6eeebd73350b. We further rely on ISTAnt dataset publicly\r\navailable at https://doi.org/10.6084/m9.figshare.26484934.v2. The synthetic experiments\r\non CausalMNIST relies on MNIST dataset LeCun [1998], publicly available. Additional\r\nexperimental details are reported in Section 5 and Appendices B-C.","external_id":{"arxiv":["2502.06343"]},"date_created":"2026-09-06T22:02:01Z","arxiv":1,"date_published":"2025-12-01T00:00:00Z","type":"conference","fulldoi":"https://doi.org/10.52202/085713-2479","das_tickbox":"1","page":"82200-82229","publication":"39th Conference on Neural Information Processing Systems","project":[{"_id":"a392d8f0-b034-11f1-b88e-d3025c6734f6","grant_number":"COE12","name":"Bilateral Artificial Intelligence (Locatello)"}],"researchdata_availability":"yes","scopus_import":"1","day":"01","abstract":[{"lang":"eng","text":"In many scientific experiments, the data annotating cost constraints the pace\r\nfor testing novel hypotheses. Yet, modern machine learning pipelines offer a\r\npromising solution—provided their predictions yield correct conclusions. We\r\nfocus on Prediction-Powered Causal Inferences (PPCI), i.e., estimating the\r\ntreatment effect in an unlabeled target experiment, relying on training data with\r\nthe same outcome annotated but potentially different treatment or effect modifiers.\r\nWe first show that conditional calibration guarantees valid PPCI at population\r\nlevel. Then, we introduce a sufficient representation constraint transferring validity\r\nacross experiments, which we propose to enforce in practice in Deconfounded\r\nEmpirical Risk Minimization, our new model-agnostic training objective. We\r\nvalidate our method on synthetic and real-world scientific data, solving impossible\r\nproblem instances for Empirical Risk Minimization even with standard invariance\r\nconstraints. In particular, for the first time, we achieve valid causal inference\r\non a scientific experiment with complex recording and no human annotations,\r\nfine-tuning a foundational model on our similar annotated experiment."}],"volume":38,"supplementarymaterial":"yes","alternative_title":["Advances in Neural Information Processing Systems"],"publication_identifier":{"issn":["1049-5258"],"isbn":["9798331338275"]},"citation":{"ieee":"R. Cadei <i>et al.</i>, “Prediction-Powered Causal Inferences,” in <i>39th Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38, pp. 82200–82229.","chicago":"Cadei, Riccardo, Ilker Demirel, Piersilvio De Bartolomeis, Lukas Lindorfer, Sylvia Cremer, Cordelia Schmid, and Francesco Locatello. “Prediction-Powered Causal Inferences.” In <i>39th Conference on Neural Information Processing Systems</i>, 38:82200–229. Neural Information Processing Systems Foundation, 2025. <a href=\"https://doi.org/10.52202/085713-2479\">https://doi.org/10.52202/085713-2479</a>.","short":"R. Cadei, I. Demirel, P. De Bartolomeis, L. Lindorfer, S. Cremer, C. Schmid, F. Locatello, in:, 39th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025, pp. 82200–82229.","apa":"Cadei, R., Demirel, I., De Bartolomeis, P., Lindorfer, L., Cremer, S., Schmid, C., &#38; Locatello, F. (2025). Prediction-Powered Causal Inferences. In <i>39th Conference on Neural Information Processing Systems</i> (Vol. 38, pp. 82200–82229). San Diego, CA, United States: Neural Information Processing Systems Foundation. <a href=\"https://doi.org/10.52202/085713-2479\">https://doi.org/10.52202/085713-2479</a>","mla":"Cadei, Riccardo, et al. “Prediction-Powered Causal Inferences.” <i>39th Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025, pp. 82200–29, doi:<a href=\"https://doi.org/10.52202/085713-2479\">10.52202/085713-2479</a>.","ista":"Cadei R, Demirel I, De Bartolomeis P, Lindorfer L, Cremer S, Schmid C, Locatello F. 2025. Prediction-Powered Causal Inferences. 39th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38, 82200–82229.","ama":"Cadei R, Demirel I, De Bartolomeis P, et al. Prediction-Powered Causal Inferences. In: <i>39th Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025:82200-82229. doi:<a href=\"https://doi.org/10.52202/085713-2479\">10.52202/085713-2479</a>"},"oa_version":"Preprint","acknowledgement":"We thank the Causal Learning and Artificial Intelligence group at ISTA for the continuous feedback\r\non the project and valuable discussions. We thank the Social Immunity group at ISTA, particularly\r\nJinook Oh, for the annotation program and Michaela Hoenigsberger for supporting our ecological\r\nexperiment. Riccardo Cadei is supported by a Google Research Scholar Award and a Google Initiated\r\nGift to Francesco Locatello. This research was funded in part by the Austrian Science Fund (FWF)\r\n10.55776/COE12). It was further partially supported by the ISTA Interdisciplinary Project Committee\r\nfor the collaborative project “ALED” between Francesco Locatello and Sylvia Cremer. For open\r\naccess purposes, the author has applied a CC BY public copyright license to any author accepted\r\nmanuscript version arising from this submission.\r\n","language":[{"iso":"eng"}]},{"oa":1,"author":[{"id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","first_name":"Riccardo","last_name":"Cadei","full_name":"Cadei, Riccardo"},{"full_name":"Demirel, Ilker","last_name":"Demirel","first_name":"Ilker"},{"last_name":"De Bartolomeis","full_name":"De Bartolomeis, Piersilvio","first_name":"Piersilvio"},{"first_name":"Lukas","id":"85f0e6d3-06b3-11ec-8982-8c5049fa4455","last_name":"Lindorfer","full_name":"Lindorfer, Lukas"},{"last_name":"Cremer","full_name":"Cremer, Sylvia","first_name":"Sylvia","id":"2F64EC8C-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-2193-3868"},{"last_name":"Schmid","full_name":"Schmid, Cordelia","first_name":"Cordelia"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello","full_name":"Locatello, Francesco"}],"publisher":"Neural Information Processing Systems Foundation","intvolume":"        38","quality_controlled":"1","has_accepted_license":"1","status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2026-10-15T09:29:52Z","year":"2025","title":"Prediction-powered causal inferences","doi":"10.52202/085713-2479","_id":"21076","conference":{"name":"NeurIPS: Neural Information Processing Systems","end_date":"2025-12-07","start_date":"2025-12-02","location":"San Diego, CA, United States"},"date_created":"2026-01-29T14:35:11Z","publication_status":"published","OA_place":"publisher","article_processing_charge":"No","month":"12","department":[{"_id":"FrLo"},{"_id":"SyCr"}],"OA_type":"free access","fulldoi":"https://doi.org/10.52202/085713-2479","das_tickbox":"1","type":"conference","date_published":"2025-12-15T00:00:00Z","publication":"39th Annual Conference on Neural Information Processing Systems","ddc":["000"],"day":"15","abstract":[{"lang":"eng","text":"In many scientific experiments, the data annotating cost constraints the pace for testing novel hypotheses. Yet, modern machine learning pipelines offer a promising solution—provided their predictions yield correct conclusions. We focus on Prediction-Powered Causal Inferences (PPCI), i.e., estimating the treatment effect in an unlabeled target experiment, relying on training data with the same outcome annotated but potentially different treatment or effect modifiers. We first show that conditional calibration guarantees valid PPCI at population level. Then, we introduce a sufficient representation constraint transferring validity across experiments, which we propose to enforce in practice in Deconfounded Empirical Risk Minimization, our new model-agnostic training objective. We validate our method on synthetic and real-world scientific data, solving impossible problem instances for Empirical Risk Minimization even with standard invariance constraints. In particular, for the first time, we achieve valid causal inference on a scientific experiment with complex recording and no human annotations, fine-tuning a foundational model on our similar annotated experiment."}],"alternative_title":["Advances in Neural Information Processing Systems"],"volume":38,"project":[{"_id":"a392d8f0-b034-11f1-b88e-d3025c6734f6","name":"Bilateral Artificial Intelligence (Locatello)","grant_number":"COE12"}],"publication_identifier":{"eissn":["1049-5258"]},"citation":{"apa":"Cadei, R., Demirel, I., De Bartolomeis, P., Lindorfer, L., Cremer, S., Schmid, C., &#38; Locatello, F. (2025). Prediction-powered causal inferences. In <i>39th Annual Conference on Neural Information Processing Systems</i> (Vol. 38). San Diego, CA, United States: Neural Information Processing Systems Foundation. <a href=\"https://doi.org/10.52202/085713-2479\">https://doi.org/10.52202/085713-2479</a>","short":"R. Cadei, I. Demirel, P. De Bartolomeis, L. Lindorfer, S. Cremer, C. Schmid, F. Locatello, in:, 39th Annual Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025.","ieee":"R. Cadei <i>et al.</i>, “Prediction-powered causal inferences,” in <i>39th Annual Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38.","chicago":"Cadei, Riccardo, Ilker Demirel, Piersilvio De Bartolomeis, Lukas Lindorfer, Sylvia Cremer, Cordelia Schmid, and Francesco Locatello. “Prediction-Powered Causal Inferences.” In <i>39th Annual Conference on Neural Information Processing Systems</i>, Vol. 38. Neural Information Processing Systems Foundation, 2025. <a href=\"https://doi.org/10.52202/085713-2479\">https://doi.org/10.52202/085713-2479</a>.","ama":"Cadei R, Demirel I, De Bartolomeis P, et al. Prediction-powered causal inferences. In: <i>39th Annual Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025. doi:<a href=\"https://doi.org/10.52202/085713-2479\">10.52202/085713-2479</a>","ista":"Cadei R, Demirel I, De Bartolomeis P, Lindorfer L, Cremer S, Schmid C, Locatello F. 2025. Prediction-powered causal inferences. 39th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38.","mla":"Cadei, Riccardo, et al. “Prediction-Powered Causal Inferences.” <i>39th Annual Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025, doi:<a href=\"https://doi.org/10.52202/085713-2479\">10.52202/085713-2479</a>."},"file_date_updated":"2026-01-29T14:35:02Z","file":[{"date_updated":"2026-01-29T14:35:02Z","access_level":"open_access","success":1,"creator":"flocatel","file_size":8489023,"file_id":"21077","relation":"main_file","date_created":"2026-01-29T14:35:02Z","file_name":"17546_Prediction_Powered_Causa.pdf","checksum":"92467fa566cd36671a6a3b9e71ae0f71","content_type":"application/pdf"}],"acknowledgement":"We thank the Causal Learning and Artificial Intelligence group at ISTA for the continuous feedback on the project and valuable discussions. We thank the Social Immunity group at ISTA, particularly Jinook Oh, for the annotation program and Michaela Hoenigsberger for supporting our ecological experiment. Riccardo Cadei is supported by a Google Research Scholar Award and a Google Initiated Gift to Francesco Locatello. This research was funded in part by the Austrian Science Fund (FWF) 10.55776/COE12). It was further partially supported by the ISTA Interdisciplinary Project Committee for the collaborative project “ALED” between Francesco Locatello and Sylvia Cremer. For open access purposes, the author has applied a CC BY public copyright license to any author accepted manuscript version arising from this submission.","language":[{"iso":"eng"}],"oa_version":"Published Version","tmp":{"short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png"}},{"day":"15","volume":38,"alternative_title":["Advances in Neural Information Processing Systems"],"abstract":[{"text":"Causal reasoning and discovery, two fundamental tasks of causal analysis,\r\noften face challenges in applications due to the complexity, noisiness, and highdimensionality of real-world data. Despite recent progress in identifying latent\r\ncausal structures using causal representation learning (CRL), what makes learned\r\nrepresentations useful for causal downstream tasks and how to evaluate them are\r\nstill not well understood. In this paper, we reinterpret CRL using a measurement\r\nmodel framework, where the learned representations are viewed as proxy measurements of the latent causal variables. Our approach clarifies the conditions under\r\nwhich learned representations support downstream causal reasoning and provides\r\na principled basis for quantitatively assessing the quality of representations using\r\na new Test-based Measurement EXclusivity (T-MEX) score. We validate T-MEX\r\nacross diverse causal inference scenarios, including numerical simulations and\r\nreal-world ecological video analysis, demonstrating that the proposed framework\r\nand corresponding score effectively assess the identification of learned representations and their usefulness for causal downstream tasks. Reproducible code can\r\nbe found at https://github.com/shimenghuang/a-measurement-perspective-of-crl.","lang":"eng"}],"project":[{"name":"Bilateral Artificial Intelligence (Locatello)","grant_number":"COE12","_id":"a392d8f0-b034-11f1-b88e-d3025c6734f6"}],"publication":"39th Annual Conference on Neural Information Processing Systems","ddc":["000"],"acknowledgement":"This research was funded in whole or in part by the Austrian Science Fund (FWF) 10.55776/COE12. For open access purposes, the author has applied a CC BY public copyright license to any accepted manuscript version arising from this submission.\r\n","language":[{"iso":"eng"}],"tmp":{"short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png"},"oa_version":"Preprint","publication_identifier":{"eissn":["1049-5258"]},"citation":{"apa":"Yao, D., Huang, S., Cadei, R., Zhang, K., &#38; Locatello, F. (2025). The third pillar of causal analysis? A measurement perspective on causal representations. In <i>39th Annual Conference on Neural Information Processing Systems</i> (Vol. 38). San Diego, CA, United States: Neural Information Processing Systems Foundation. <a href=\"https://doi.org/10.52202/085713-1444\">https://doi.org/10.52202/085713-1444</a>","short":"D. Yao, S. Huang, R. Cadei, K. Zhang, F. Locatello, in:, 39th Annual Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025.","ieee":"D. Yao, S. Huang, R. Cadei, K. Zhang, and F. Locatello, “The third pillar of causal analysis? A measurement perspective on causal representations,” in <i>39th Annual Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38.","chicago":"Yao, Dingling, Shimeng Huang, Riccardo Cadei, Kun Zhang, and Francesco Locatello. “The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations.” In <i>39th Annual Conference on Neural Information Processing Systems</i>, Vol. 38. Neural Information Processing Systems Foundation, 2025. <a href=\"https://doi.org/10.52202/085713-1444\">https://doi.org/10.52202/085713-1444</a>.","ama":"Yao D, Huang S, Cadei R, Zhang K, Locatello F. The third pillar of causal analysis? A measurement perspective on causal representations. In: <i>39th Annual Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025. doi:<a href=\"https://doi.org/10.52202/085713-1444\">10.52202/085713-1444</a>","ista":"Yao D, Huang S, Cadei R, Zhang K, Locatello F. 2025. The third pillar of causal analysis? A measurement perspective on causal representations. 39th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38.","mla":"Yao, Dingling, et al. “The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations.” <i>39th Annual Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025, doi:<a href=\"https://doi.org/10.52202/085713-1444\">10.52202/085713-1444</a>."},"has_accepted_license":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","quality_controlled":"1","status":"public","doi":"10.52202/085713-1444","title":"The third pillar of causal analysis? A measurement perspective on causal representations","date_updated":"2026-10-15T09:31:39Z","year":"2025","_id":"21068","corr_author":"1","oa":1,"author":[{"id":"d3e02e50-48a8-11ee-8f62-c108061797fa","first_name":"Dingling","full_name":"Yao, Dingling","last_name":"Yao"},{"orcid":"0000-0001-6919-821X","id":"989c2a06-fb4e-11ef-a992-ab766442255b","first_name":"Shimeng","full_name":"Huang, Shimeng","last_name":"Huang"},{"full_name":"Cadei, Riccardo","last_name":"Cadei","first_name":"Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b"},{"first_name":"Kun","last_name":"Zhang","full_name":"Zhang, Kun"},{"orcid":"0000-0002-4850-0683","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","last_name":"Locatello"}],"intvolume":"        38","publisher":"Neural Information Processing Systems Foundation","fulldoi":"https://doi.org/10.52202/085713-1444","das_tickbox":"1","related_material":{"link":[{"relation":"software","url":"https://github.com/shimenghuang/a-measurement-perspective-of-crl"}]},"arxiv":1,"date_published":"2025-12-15T00:00:00Z","type":"conference","conference":{"location":"San Diego, CA, United States","start_date":"2025-12-02","end_date":"2025-12-07","name":"NeurIPS: Neural Information Processing Systems"},"external_id":{"arxiv":["2505.17708"]},"date_created":"2026-01-29T14:24:56Z","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2505.17708","open_access":"1"}],"publication_status":"published","OA_type":"green","department":[{"_id":"FrLo"}],"article_processing_charge":"No","month":"12","OA_place":"repository"},{"author":[{"full_name":"Demirel, Berker","last_name":"Demirel","first_name":"Berker","id":"8b4bc47f-3200-11ee-973b-8f0e7be21a9f"},{"full_name":"Fumero, Marco ","last_name":"Fumero","first_name":"Marco "},{"orcid":"0000-0002-4850-0683","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","last_name":"Locatello"}],"corr_author":"1","oa":1,"intvolume":"        38","publisher":"Neural Information Processing Systems Foundation","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","quality_controlled":"1","has_accepted_license":"1","doi":"10.52202/085713-3125","date_updated":"2026-10-15T09:32:34Z","title":"Out-of-Distribution detection with relative angles","year":"2025","_id":"21070","conference":{"start_date":"2025-12-02","location":"San Diego, CA, United States","end_date":"2025-12-07","name":"NeurIPS: Neural Information Processing Systems"},"external_id":{"arxiv":["2410.04525"]},"date_created":"2026-01-29T14:26:47Z","publication_status":"published","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2410.04525"}],"OA_type":"green","department":[{"_id":"FrLo"}],"month":"12","OA_place":"repository","article_processing_charge":"No","fulldoi":"https://doi.org/10.52202/085713-3125","das_tickbox":"1","related_material":{"link":[{"url":"https://github.com/berkerdemirel/ORA-OOD-Detection-with-Relative-Angles","relation":"software"}]},"arxiv":1,"type":"conference","date_published":"2025-12-01T00:00:00Z","ddc":["000"],"publication":"39th Annual Conference on Neural Information Processing Systems","day":"01","volume":38,"alternative_title":["Advances in Neural Information Processing Systems"],"abstract":[{"lang":"eng","text":"Deep learning systems deployed in real-world applications often encounter data that is different from their in-distribution (ID). A reliable model should ideally abstain from making decisions in this out-of-distribution (OOD) setting. Existing state-of-the-art methods primarily focus on feature distances, such as k-th nearest neighbors and distances to decision boundaries, either overlooking or ineffectively using in-distribution statistics. In this work, we propose a novel angle-based metric for OOD detection that is computed relative to the in-distribution structure. We demonstrate that the angles between feature representations and decision boundaries, viewed from the mean of in-distribution features, serve as an effective discriminative factor between ID and OOD data. We evaluate our method on nine ImageNet-pretrained models. Our approach achieves the lowest FPR in 5 out of 9 ImageNet models, obtains the best average FPR overall, and consistently ranking among the top 3 across all evaluated models. Furthermore, we highlight the benefits of contrastive representations by showing strong performance with ResNet SCL and CLIP architectures. Finally, we demonstrate that the scale-invariant nature of our score enables an ensemble strategy via simple score summation. "}],"project":[{"_id":"a392d8f0-b034-11f1-b88e-d3025c6734f6","name":"Bilateral Artificial Intelligence (Locatello)","grant_number":"COE12"}],"publication_identifier":{"eissn":["1049-5258"]},"citation":{"mla":"Demirel, Berker, et al. “Out-of-Distribution Detection with Relative Angles.” <i>39th Annual Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025, doi:<a href=\"https://doi.org/10.52202/085713-3125\">10.52202/085713-3125</a>.","ista":"Demirel B, Fumero M, Locatello F. 2025. Out-of-Distribution detection with relative angles. 39th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38.","ama":"Demirel B, Fumero M, Locatello F. Out-of-Distribution detection with relative angles. In: <i>39th Annual Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025. doi:<a href=\"https://doi.org/10.52202/085713-3125\">10.52202/085713-3125</a>","chicago":"Demirel, Berker, Marco  Fumero, and Francesco Locatello. “Out-of-Distribution Detection with Relative Angles.” In <i>39th Annual Conference on Neural Information Processing Systems</i>, Vol. 38. Neural Information Processing Systems Foundation, 2025. <a href=\"https://doi.org/10.52202/085713-3125\">https://doi.org/10.52202/085713-3125</a>.","ieee":"B. Demirel, M. Fumero, and F. Locatello, “Out-of-Distribution detection with relative angles,” in <i>39th Annual Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38.","short":"B. Demirel, M. Fumero, F. Locatello, in:, 39th Annual Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025.","apa":"Demirel, B., Fumero, M., &#38; Locatello, F. (2025). Out-of-Distribution detection with relative angles. In <i>39th Annual Conference on Neural Information Processing Systems</i> (Vol. 38). San Diego, CA, United States: Neural Information Processing Systems Foundation. <a href=\"https://doi.org/10.52202/085713-3125\">https://doi.org/10.52202/085713-3125</a>"},"acknowledgement":"This research was funded in whole or in part by the Austrian Science Fund (FWF) 10.55776/COE12. For open access purposes, the author has applied a CC BY public copyright license to any accepted manuscript version arising from this submission.\r\n","language":[{"iso":"eng"}],"tmp":{"short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png"},"oa_version":"Preprint"}]