Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
DyTrim is proposed, a principle-based dynamic pruning framework that reallocates gradient budget through class-aware pruning on labeled data and confidence-based soft pruning on unlabeled data and provides theoretical guarantees that DyTrim reduces class bias and improves generalization.
Yue Cheng, Jia-Jun Zhang, Xiao-Hui Gao et al.
· 1 citation