Projections of Model Spaces for Latent Graph Inference

Graph Neural Networks leverage the connectivity structure of graphs as an inductive bias. Latent graph inference focuses on learning an adequate graph structure to diffuse information on and improve the downstream performance of the model. In this work we employ stereographic projections of the hype...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-04
Main Authors: Haitz Sáez de Ocáriz Borde, Arroyo, Álvaro, Posner, Ingmar
Format: Article
Language:English
Subjects:
Graph neural networks
Graph theory
Graphs
Inference
Riemann manifold
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Graph Neural Networks leverage the connectivity structure of graphs as an inductive bias. Latent graph inference focuses on learning an adequate graph structure to diffuse information on and improve the downstream performance of the model. In this work we employ stereographic projections of the hyperbolic and spherical model spaces, as well as products of Riemannian manifolds, for the purpose of latent graph inference. Stereographically projected model spaces achieve comparable performance to their non-projected counterparts, while providing theoretical guarantees that avoid divergence of the spaces when the curvature tends to zero. We perform experiments on both homophilic and heterophilic graphs.
ISSN:2331-8422