VJE is a new variational non-contrastive SSL method that models target embeddings with a directional-radial Student-t distribution to enable structured uncertainty estimation directly in the learned representation space.
arXiv preprint arXiv:2506.07413 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
citing papers explorer
-
Joint Embedding Variational Bayes
VJE is a new variational non-contrastive SSL method that models target embeddings with a directional-radial Student-t distribution to enable structured uncertainty estimation directly in the learned representation space.
-
On the Properties of Feature Attribution for Supervised Contrastive Learning
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.