Mingsong Yan

activity

20222026

most citedParameter Choices for Sparse Regularization with the

ℓ_{1}

Norm

7 citations · 10 across the 8 of their papers we have counts for

collaborators

Showing cs.LGShow all

3 papers · 1 filter

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…

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…

cs.LG2024

Sparse Deep Learning Models with the $ℓ_{1}$ Regularization

Lixin Shen, Rui Wang, Yuesheng Xu +1

Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the s…

Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence

On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks

Sparse Deep Learning Models with the ℓ1​ Regularization

Sparse Deep Learning Models with the $ℓ_{1}$ Regularization