Marrying causal representation learning with dynamical systems for science

conference paper Marrying causal representation learning with dynamical systems for science Advances in Neural Information Processing Systems published yes Dingling Yao author d3e02e50-48a8-11ee-8f62-c108061797fa Caroline J Muller author f978ccb0-3f7f-11eb-b193-b0e2bd13182b0000-0001-5836-5350 Francesco Locatello author 26cfd52f-2483-11ee-8040-88983bcc06d40000-0002-4850-0683 CaMu department FrLo department NeurIPS: Neural Information Processing Systems Causal representation learning promises to extend causal models to hidden causal variables from raw entangled measurements. However, most progress has focused on proving identifiability results in different settings, and we are not aware of any successful real-world application. At the same time, the field of dynamical systems benefited from deep learning and scaled to countless applications but does not allow parameter identification. In this paper, we draw a clear connection between the two and their key assumptions, allowing us to apply identifiable methods developed in causal representation learning to dynamical systems. At the same time, we can leverage scalable differentiable solvers developed for differential equations to build models that are both identifiable and practical. Overall, we learn explicitly controllable models that isolate the trajectory-specific parameters for further downstream tasks such as out-of-distribution classification or treatment effect estimation. We experiment with a wind simulator with partially known factors of variation. We also apply the resulting model to real-world climate data and successfully answer downstream causal questions in line with existing literature on climate change. Code is available at https://github.com/CausalLearningAI/crl-dynamical-systems. https://research-explorer.ista.ac.at/download/19005/19006/2024_NeurIPS_Yao.pdf application/pdfno https://creativecommons.org/licenses/by/4.0/ Neural Information Processing Systems Foundation2024Vancouver, Canada eng 38th Conference on Neural Information Processing Systems 2405.13888 37 https://github.com/CausalLearningAI/crl-dynamical-systems Yao D, Muller CJ, Locatello F. Marrying causal representation learning with dynamical systems for science. In: 38th Conference on Neural Information Processing Systems. Vol 37. Neural Information Processing Systems Foundation; 2024. Yao D, Muller CJ, Locatello F. 2024. Marrying causal representation learning with dynamical systems for science. 38th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 37. Yao, Dingling, et al. “Marrying Causal Representation Learning with Dynamical Systems for Science.” 38th Conference on Neural Information Processing Systems, vol. 37, Neural Information Processing Systems Foundation, 2024. Yao, D., Muller, C. J., & Locatello, F. (2024). Marrying causal representation learning with dynamical systems for science. In 38th Conference on Neural Information Processing Systems (Vol. 37). Vancouver, Canada: Neural Information Processing Systems Foundation. D. Yao, C. J. Muller, and F. Locatello, “Marrying causal representation learning with dynamical systems for science,” in 38th Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37. Yao, Dingling, Caroline J Muller, and Francesco Locatello. “Marrying Causal Representation Learning with Dynamical Systems for Science.” In 38th Conference on Neural Information Processing Systems, Vol. 37. Neural Information Processing Systems Foundation, 2024. D. Yao, C.J. Muller, F. Locatello, in:, 38th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2024. 190052025-02-05T07:49:00Z2025-07-10T11:51:32Z