Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning
Torben Berndt, Benjamin Walker, Tiexin Qin, Jan Stühmer, Andrey Kormilitzin
Abstract
Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential Equations (Graph Neural CDEs) successfully adapted Neural CDEs from paths on Euclidean domains to paths on graph domains. Building on this foundation, we introduce \textit{Permutation Equivariant Graph Neural CDEs}, which project Graph Neural CDEs onto permutation equivariant function spaces. This significantly reduces the model's parameter count without compromising representational power, resulting in more efficient training and improved generalisation. We empirically demonstrate the advantages of our approach through experiments on simulated dynamical systems and real-world tasks, showing improved performance in both interpolation and extrapolation scenarios.
BibTeX
@inproceedings{
berndt2025permutation,
title={Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning},
author={Torben Berndt and Benjamin Walker and Tiexin Qin and Jan St{\"u}hmer and Andrey Kormilitzin},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=NC7FPrUpKi}
}