Donald Loveland

On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks

2023 · arXiv (Cornell University)

Graph Neural Network (GNN) research has highlighted a relationship between high homophily (i.e., the tendency of nodes of the same class to connect) and strong predictive performance in node classification. However, recent work has found …

Network Design through Graph Neural Networks: Identifying Challenges and Improving Performance

2023 · arXiv (Cornell University)

Graph Neural Network (GNN) research has produced strategies to modify a graph's edges using gradients from a trained GNN, with the goal of network design. However, the factors which govern gradient-based editing are understudied, obscuring …