Overview

It studies how skewed class frequencies, long tails, and rare events bias models toward majority classes, a challenge in medical diagnosis, fraud detection, and computer vision. Common approaches rebalance data through over- or undersampling and synthetic examples, adjust objectives with class weights, focal or logit-adjusted losses, and improve representations with prototypes, contrastive learning, or class-aware sampling. Active learning, calibration, and federated or semi-supervised methods address settings with limited labels, distributed data, or shifting class priors. Results depend strongly on data structure and deployment conditions: reweighting and synthetic data can improve minority recall but may also harm performance or calibration, so evaluations need class-wise and operational metrics, not accuracy alone.

Latest papers

CardsList

276 papers21 papers in the last four weeks, down 16% on the four weeks before. 0.2% of all new papers.

  1. When majority rules, minority loses: bias amplification of gradient descent

    May 19, 2025François Bachoc, Jérôme Bolte, Ryan Boustany +1Class-Imbalanced LearningGradient Descent

  2. iCost: A Novel Instance-Complexity-Based Cost-Sensitive Learning Framework

    Sep 19, 2024Asif Newaz, Asif Ur Rahman Adib, Taskeed JabidClass-Imbalanced LearningCost-Sensitive Learning

  3. AIR: Analytic Imbalance Rectifier for Continual Learning

    Aug 19, 2024Di Fang, Yinan Zhu, Zhiping Lin +3Class-Imbalanced LearningClass-Incremental Learning

  4. Robust performance metrics for imbalanced classification problems

    Apr 11, 2024Hajo Holzmann, Bernhard KlarClass-Imbalanced LearningBinary Classification

  5. Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance

    Aug 26, 2020Selim F. Yilmaz, E. Batuhan Kaynak, Aykut Koç +2Multilingual Sentiment AnalysisSentiment Analysis