top of page
Wireframe - 8.png

When do neural ordinary differential equations generalize on complex networks?

Moritz Laber, Tina Eliassi-Rad, Brennan Klein

Working Paper

|

February 9, 2026

Neural ordinary differential equations (neural ODEs) can effectively learn dynamical systems from time series data, but their behavior on graph-structured data remains poorly understood, especially when applied to graphs with different size or structure than encountered during training. We study neural ODEs (𝚗𝙾𝙳𝙴s) with vector fields following the Barabási-Barzel form, trained on synthetic data from five common dynamical systems on graphs. Using the 𝕊1-model to generate graphs with realistic and tunable structure, we find that degree heterogeneity and the type of dynamical system are the primary factors in determining 𝚗𝙾𝙳𝙴s' ability to generalize across graph sizes and properties. This extends to 𝚗𝙾𝙳𝙴s' ability to capture fixed points and maintain performance amid missing data. Average clustering plays a secondary role in determining 𝚗𝙾𝙳𝙴 performance. Our findings highlight 𝚗𝙾𝙳𝙴s as a powerful approach to understanding complex systems but underscore challenges emerging from degree heterogeneity and clustering in realistic graphs.

citation

Laber, M., Eliassi-Rad, T., & Klein, B. (2026). When do neural ordinary differential equations generalize on complex networks? [Preprint]. arXiv. https://doi.org/10.48550/arxiv.2602.08980

topics

Research Methods & Data

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

related work

Rectangle 35

Measuring Agency-Amplifying AI Literacy: The HuskyAI Coaching Platform for Workforce Readiness

July 2026

HuskyAI is a web platform on which students develop AI knowledge by working through authentic

Artificial Intelligence

Artificial Intelligence

Working Paper

Rectangle 35

Measuring Agency-Amplifying AI Literacy: The HuskyAI Coaching Platform for Workforce Readiness

July 2026

HuskyAI is a web platform on which students develop AI knowledge by working through authentic

Artificial Intelligence

Artificial Intelligence

Working Paper

Rectangle 35

Measuring Agency-Amplifying AI Literacy: The HuskyAI Coaching Platform for Workforce Readiness

July 2026

HuskyAI is a web platform on which students develop AI knowledge by working through authentic

Artificial Intelligence

Artificial Intelligence

Working Paper

bottom of page