Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Kamilia Zaripova, Luca Cosmo, Anees Kazi, Seyed-Ahmad Ahmadi, Michael M. Bronstein, Nassir Navab

Abstract: Highlights•Demonstrates the influence of population graphs on the downstream task•Works directly on graph-valued data and benefits from the latent population graph•Introduces a degree distribution regularizer for better knowledge discovery