3 papers
stat.ML2026
Graph Attention Network for Node Regression on Random Geometric Graphs with ErdÅs--Rényi contamination
Somak Laha, Suqi Liu, Morgane Austern
Graph attention networks (GATs) are widely used and often appear robust to noise in node covariates and edges, yet rigorous statistical guarantees demonstrating a provable advantag…
stat.ML2026
GRAND: Graph Release with Assured Node Differential Privacy
Suqing Liu, Xuan Bi, Tianxi Li
Differential privacy is a well-established framework for safeguarding sensitive information in data. While extensively applied across various domains, its application to network da…
cs.LG2025
Perfect Recovery for Random Geometric Graph Matching with Shallow Graph Neural Networks
Suqi Liu, Morgane Austern
We study the graph matching problem in the presence of vertex feature information using shallow graph neural networks. Specifically, given two graphs that are independent perturbat…