UASPL selects training samples by an evidential loss that couples label fit with adaptive uncertainty-weighted KL regularization, yielding an easy-to-hard preference and stronger average classification results than loss-only SPL.
Title resolution pending
1 Pith paper cite this work, alongside 152 external citations. Polarity classification is still indexing.
1
Pith paper citing it
152
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks
UASPL selects training samples by an evidential loss that couples label fit with adaptive uncertainty-weighted KL regularization, yielding an easy-to-hard preference and stronger average classification results than loss-only SPL.