CUSP is a graph neural network that combines Ollivier-Ricci curvature with spectral filters on a product of hyperbolic, spherical, and Euclidean spaces, claiming SOTA results on eight node and link prediction benchmarks.
Analysis of the physical Laplacian and the heat flow on a locally finite graph
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We study the physical Laplacian and the corresponding heat flow on an infinite, locally finite graph with possibly unbounded valence.
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Spectro-Riemannian Graph Neural Networks
CUSP is a graph neural network that combines Ollivier-Ricci curvature with spectral filters on a product of hyperbolic, spherical, and Euclidean spaces, claiming SOTA results on eight node and link prediction benchmarks.