GEAR aligns Ricci curvatures in latent spaces of models to create a unified transfer learning architecture, achieving 14.4% and 8.3% performance gains on 23 molecular task pairs under random and scaffold splits.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometric Embedding Alignment via Curvature Matching in Transfer Learning
GEAR aligns Ricci curvatures in latent spaces of models to create a unified transfer learning architecture, achieving 14.4% and 8.3% performance gains on 23 molecular task pairs under random and scaffold splits.