Two neighbour-based approximations, HPA and SPA, make Gaussian Process variational autoencoders scalable while preserving local latent correlations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling
Two neighbour-based approximations, HPA and SPA, make Gaussian Process variational autoencoders scalable while preserving local latent correlations.