Papers › Optimising Neural Fractional Differential Equations for Performance and Efficiency

Optimising Neural Fractional Differential Equations for Performance and Efficiency

20 Oct 2024PMLR Volume 255: 1st ECAI Workshop on “Machine Learning Meets Differential Equations: From Theory to Applications” 2024 10archive 2025-07-28

Bernd Zimmering, Cecília Coelho, Oliver Niggemann

Neural Ordinary Differential Equations (NODEs) are well-established architectures that fit an ODE, modelled by a neural network (NN), to data, effectively modelling complex dynamical systems. Recently, Neural Fractional Differential Equations (NFDEs) were proposed, inspired by NODEs, to incorporate non-integer order differential equations, capturing memory effects and long-range dependencies. In this work, we present an optimised implementation of the NFDE solver, achieving up to 570 times faster computations and up to 79 times higher accuracy. Additionally, the solver supports efficient multidimensional computations and batch processing. Furthermore, we enhance the experimental design to ensure a fair comparison of NODEs and NFDEs by implementing rigorous hyperparameter tuning and using consistent numerical methods. Our results demonstrate that for systems exhibiting fractional dynamics, NFDEs significantly outperform NODEs, particularly in extrapolation tasks on unseen time horizons. Although NODEs can learn fractional dynamics when time is included as a feature to the NN, they encounter difficulties in extrapolation due to reliance on explicit time dependence. The code is available at https://github.com/zimmer-ing/Neural-FDE

PaperPDFCode

Code

zimmer-ing/FDEint officialpytorch report
zimmer-ing/neural-fde mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Experimental Design

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

NODETree-structured Parzen Estimator Approach (TPE)

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections