Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning
arXiv stat.ML4w4 min read
arXiv:2607.01762v1 Announce Type: cross Abstract: Many representation learning problems involve directed relations, such as lexical entailment, sentence entailment, ontology hierarchy, and citation links. Standard Euclidean, cosine, and Mahalanobis heads are symmetric, while generic neural scorers can model directionality but provide limited geometric structure. This paper proposes a role-aware neural convex divergence head for asymmetric representation learning. The head applies source- and target-role projections before evaluating an input-convex neural Bregman divergence, yielding a nonnega
