Identifying ODEs from Unstructured Data with Causal Representation Learning
Abstract
We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE discovery typically assume direct measurements of the variables, or do not provide theoretical guarantees on the learned variables and equations. While Causal Representation Learning (CRL) methods provide guarantees on identifying variables from high-dimensional observations up to component-wise diffeomorphisms, we show that in general these variables cannot be used directly as input to equation discovery methods, which typically assume that the variables will lead to sparse equations. So we introduce SParse Equivalent Equation Discovery AutoEncoder (SPEED-AE), a framework that combines a pretrained CRL method with a component-wise autoencoder that learns transformations of variables that are amenable to sparse ODE discovery. We show that for polynomial ODEs, this additional step allows us to restrict the identifiability of each variable from polynomial to monomial diffeomorphisms. Experiments on Lotka-Volterra, Lorenz, and a two-pendulum system show that SPEED-AE improves on the disentanglement of the CRL methods and that it recovers ODEs that are closest to the ground truth, while achieving state-of-the-art forecasting performance.
Related
- Causal Representation Learning for Generalisable Recommendation
- Leveraging generative AI for causal inference with unstructured data
- GenAI Powered Dynamic Causal Inference with Unstructured Data
- The Role of Assignment in Defining and Identifying Causal Effects in Randomized Trials
- Continuous Learning of Gravity Field Irregularities Around Small Bodies via Neural Hamiltonian ODEs
BibTeX
@misc{trenta2026identifying,
title = {{Identifying ODEs from Unstructured Data with Causal Representation Learning}},
author = {Alessandro Trenta and Riccardo Massidda and Davide Bacciu and Sara Magliacane},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.37083},
eprint = {2609.37083},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.37083},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Identifying ODEs from Unstructured Data with Causal Representation Learning
AU - Alessandro Trenta
AU - Riccardo Massidda
AU - Davide Bacciu
AU - Sara Magliacane
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.37083
UR - https://arxiv.org/abs/2609.37083
AB - We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE discovery typically assume direct measurements of the variables, or do not provide theoretical guarantees on the learned variables and equations. While Causal Representation Learning (CRL) methods provide guarantees on identifying variables from high-dimensional observations up to component-wise diffeomorphisms, we show that in general these variables cannot be used directly as input to equation discovery methods, which typically assume that the variables will lead to sparse equations. So we introduce SParse Equivalent Equation Discovery AutoEncoder (SPEED-AE), a framework that combines a pretrained CRL method with a component-wise autoencoder that learns transformations of variables that are amenable to sparse ODE discovery. We show that for polynomial ODEs, this additional step allows us to restrict the identifiability of each variable from polynomial to monomial diffeomorphisms. Experiments on Lotka-Volterra, Lorenz, and a two-pendulum system show that SPEED-AE improves on the disentanglement of the CRL methods and that it recovers ODEs that are closest to the ground truth, while achieving state-of-the-art forecasting performance.
ER -