The paper proposes a role-aware neural convex divergence head using source/target projections and input-convex neural Bregman divergence to model asymmetric relations while preserving nonnegativity and convexity properties.
Tversky, Features of similarity, Psychological Review 84 (1977) 327– 352
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning
The paper proposes a role-aware neural convex divergence head using source/target projections and input-convex neural Bregman divergence to model asymmetric relations while preserving nonnegativity and convexity properties.