AI RESEARCH
On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks
arXiv CS.LG
•
ArXi:2510.03923v2 Announce Type: replace Continuous-depth graph neural networks, also known as Graph Neural Differential Equations (GNDEs), combine the structural inductive bias of Graph Neural Networks (GNNs) with the continuous-depth architecture of Neural ODEs, offering a scalable and principled framework for modeling dynamics on graphs. In this paper, we present a rigorous convergence analysis of GNDEs with time-varying parameters in the infinite-node limit, providing theoretical insights into their size transferability. To this end, we.