3 papers
cs.LG2026
Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence
Mingsong Yan, Zhida Wang, Sui Tang
Graph Neural Differential Equations (GNDEs) model continuous-time graph dynamics by parameterizing Neural ODE velocity fields with Graph Neural Networks. Their local, size-independ…
math.OC2026
Unified Ergodic Primal-Dual Gap Rates with Unhalved Primal Stepsizes
Sirong Dai, Ming Yan
We study ergodic primal-dual gap rates for first-order primal-dual methods applied to \[ \min_x f(x)+g(x)+h(Ax), \] where is smooth and convex, and are proper, closed,…
cs.LG2025
On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks
Mingsong Yan, Charles Kulick, Sui Tang
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 co…