Tag
The paper introduces role-aware neural convex divergence heads that apply source and target role projections before evaluating an input-convex neural Bregman divergence, enabling structured and interpretable asymmetric distance learning for tasks like lexical entailment, sentence entailment, and ontology hierarchy. Experiments show consistent improvements in directional accuracy over plain ICNN-Bregman heads across semantic and ontology benchmarks.
Proposes a 'lift' method for training input-convex neural networks (ICNNs) that uses an unconstrained hypernetwork to emit non-negative inter-layer weights, softening the loss landscape and escaping gradient attenuation, achieving lower test loss than projected gradient descent and softplus reparametrization.