Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
cs.LG, cs.AI
Submitted: 2026-08-31
Updated: 2026-08-31
Comments: 32 pages, 19 figures
Journal ref: International Conference on Learning Representations. 2026, 2026: 48426-48457
Project page: https://jiajun0425.github.io/DyTrim
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
- SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency
- What makes ImageNet good for transfer learning?
- Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
- Prioritized Experience Replay
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
- InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning
- Wide Residual Networks
- mixup: Beyond Empirical Risk Minimization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks