PuSH - Publication Server of Helmholtz Zentrum München

d'Ascoli,  S.* ; Becker, S. ; Mathis, A.* ; Schwaller, P.* ; Kilbertus, N.

ODEFormer: Symbolic regression of dynamical systems with transformers.

In: (12th International Conference on Learning Representations, ICLR 2024, 07-11 May 2024, Hybrid, Vienna). 2024.
Publ. Version/Full Text
We introduce ODEFormer, the first transformer able to infer multidimensional ordinary differential equation (ODE) systems in symbolic form from the observation of a single solution trajectory. We perform extensive evaluations on two datasets: (i) the existing 'Strogatz' dataset featuring two-dimensional systems; (ii) ODEBench, a collection of one- to four-dimensional systems that we carefully curated from the literature to provide a more holistic benchmark. ODEFormer consistently outperforms existing methods while displaying substantially improved robustness to noisy and irregularly sampled observations, as well as faster inference. We release our code, model and benchmark at https://github.com/sdascoli/odeformer. © 2024 12th International Conference on Learning Representations, ICLR 2024.
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Conference Title 12th International Conference on Learning Representations, ICLR 2024
Conference Date 07-11 May 2024
Conference Location Hybrid, Vienna
Non-patent literature Publications
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute of Computational Biology (ICB)