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. In this work we employ stereographic projections of the hyperbolic and spherical model spaces, as well as produc...
Main Authors: | Posner, H, Arroyo, A, Sáez De Ocáriz Borde, H |
---|---|
פורמט: | Conference item |
שפה: | English |
יצא לאור: |
OpenReview
2023
|
פריטים דומים
-
Neural latent geometry search: product manifold inference via Gromov-Hausdorff-informed Bayesian optimization
מאת: Sáez de Ocáriz Borde, H, et al.
יצא לאור: (2024) -
GENESIS: generative scene inference and sampling of object-centric latent representations
מאת: Engelcke, M, et al.
יצא לאור: (2020) -
DreamUp3D: object-centric generative models for single-view 3D scene understanding and real-to-sim transfer
מאת: Wu, Y, et al.
יצא לאור: (2024) -
Efficient state-space inference of periodic latent force models
מאת: Reece, S, et al.
יצא לאור: (2014) -
Latent source models for nonparametric inference
מאת: Chen, George H
יצא לאור: (2015)