SMILE aligns latent embeddings across multi-source EHR feature spaces via spherical mixtures of von Mises-Fisher distributions, provides non-asymptotic error bounds, and enables consistent synonym cluster recovery.
High dimensional
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces
SMILE aligns latent embeddings across multi-source EHR feature spaces via spherical mixtures of von Mises-Fisher distributions, provides non-asymptotic error bounds, and enables consistent synonym cluster recovery.