4 papers
Sampling Transferable Graph Neural Networks with Limited Graph Information
Haoyu Wang, Renyuan Ma, Gonzalo Mateos +1
Graph neural networks (GNNs) achieve strong performance on graph learning tasks, but training on large-scale networks remains computationally challenging. Transferability results s…
Kronecker-product random matrices and a matrix least squares problem
Zhou Fan, Renyuan Ma
We study the eigenvalue distribution and resolvent of a Kronecker-product random matrix model $A \otimes I_{n \times n}+I_{n \times n} \otimes B+Î\otimes Î\in \mathbb{C}^{n^2 \ti…
Anisotropic local law for non-separable sample covariance matrices
Zhou Fan, Renyuan Ma, Elliot Paquette +1
We establish local laws for sample covariance matrices $K = N^{-1}\sum_{i=1}^N \g_i\g_i^*$ where the random vectors $\g_1, \ldots, \g_N \in \R^n$ are independent with common covari…
A Generative Model for Controllable Feature Heterophily in Graphs
Haoyu Wang, Renyuan Ma, Gonzalo Mateos +1
We introduce a principled generative framework for graph signals that enables explicit control of feature heterophily, a key property underlying the effectiveness of graph learning…