Skip to main navigation Skip to search Skip to main content

Neural Context Flows for Learning Generalizable Dynamical Systems

Research output: Working paperPreprint

2 Downloads (Pure)

Abstract

Neural Ordinary Differential Equations typically struggle to generalize to new dynamical behaviors created by parameter changes in the underlying system, even when the dynamics are close to previously seen behaviors. The issue gets worse when the changing parameters are unobserved, i.e., their value or influence is not directly measurable when collecting data. We introduce Neural Context Flow (NCF), a framework that encodes said unobserved parameters in a latent context vector as input to a vector field. NCFs leverage differentiability of the vector field with respect to the parameters, along with first-order Taylor expansion to allow any context vector to influence trajectories from other parameters. We validate our method and compare it to established Multi-Task and Meta-Learning alternatives, showing competitive performance in mean squared error for in-domain and out-of-distribution evaluation on the Lotka-Volterra, Glycolytic Oscillator, and Gray-Scott problems. This study holds practical implications for foundational models in science and related areas that benefit from conditional neural ODEs. Our code is openly available at https://github.com/ddrous/ncflow.
Original languageEnglish
PublisherarXiv.org
DOIs
Publication statusPublished - 3 May 2024

Bibliographical note

14 pages, 5 figures

Keywords

  • cs.LG
  • math.DS

Fingerprint

Dive into the research topics of 'Neural Context Flows for Learning Generalizable Dynamical Systems'. Together they form a unique fingerprint.

Cite this