2026
CoLA: Co-Calibrated Logit Adjustment for Long-Tailed Semi-Supervised Learning
ICLR 2026poster
Long-tailed semi-supervised learning is hampered by a vicious cycle of confirmation bias, where skewed pseudo-labeling progressively marginalizes tail classes. This challenge is compounded in real-world scenarios by a class distribution mismatch between labeled and unlabeled data, rendering the bias…