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...
Prif Awduron: | Posner, H, Arroyo, A, Sáez De Ocáriz Borde, H |
---|---|
Fformat: | Conference item |
Iaith: | English |
Cyhoeddwyd: |
OpenReview
2023
|
Eitemau Tebyg
-
Neural latent geometry search: product manifold inference via Gromov-Hausdorff-informed Bayesian optimization
gan: Sáez de Ocáriz Borde, H, et al.
Cyhoeddwyd: (2024) -
GENESIS: generative scene inference and sampling of object-centric latent representations
gan: Engelcke, M, et al.
Cyhoeddwyd: (2020) -
DreamUp3D: object-centric generative models for single-view 3D scene understanding and real-to-sim transfer
gan: Wu, Y, et al.
Cyhoeddwyd: (2024) -
Efficient state-space inference of periodic latent force models
gan: Reece, S, et al.
Cyhoeddwyd: (2014) -
Latent source models for nonparametric inference
gan: Chen, George H
Cyhoeddwyd: (2015)