GLINKX: A Scalable Unified Framework For Homophilous and Heterophilous Graphs

no code implementations • 1 Nov 2022 • Marios Papachristou, Rishab Goel, Frank Portman, Matthew Miller, Rong Jin

On the other hand, shallow (or node-level) models using ego features and adjacency embeddings work well in heterophilous graphs.

Graph Learning Knowledge Graph Embeddings

Party On: The Labor Market Returns to Social Networks in Adolescence

no code implementations • 17 Oct 2022 • Adriana Lleras-Muney, Matthew Miller, Shuyang Sheng, Veronica Sovero

We investigate the returns to adolescent friendships on earnings in adulthood using data from the National Longitudinal Study of Adolescent to Adult Health.