Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature
Entropic Curvature is introduced, a global, transport-based curvature obtained by extending the Lott-Sturm-Villani framework to graphs through the displacement convexity of entropy along Wasserstein geodesics, and an expansion paradox proving that sparsity, strong spectral expansion, and positive entropic curvature can...