mlsanityData to 14 Oct 2026

Rethinking Class Imbalance in Machine Learning

arXiv 2305.03900 ↗First posted 6 May 2023cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Imbalance learning is a subfield of machine learning that focuses on learning tasks in the presence of class imbalance. Nearly all existing studies refer to class imbalance as a proportion imbalance, where the proportion of training samples in each class is not balanced. The ignorance of the proportion imbalance will result in unfairness between/among classes and poor generalization capability. Previous literature has presented numerous methods for either theoretical/empirical analysis or new methods for imbalance learning. This study presents a new taxonomy of class imbalance in machine learning with a broader scope. Four other types of imbalance, namely, variance, distance, neighborhood, and quality imbalances between/among classes, which may exist in machine learning tasks, are summarized. Two different levels of imbalance including global and local are also presented. Theoretical analysis is used to illustrate the significant impact of the new imbalance types on learning fairness. Moreover, our taxonomy and theoretical conclusions are used to analyze the shortcomings of several classical methods. As an example, we propose a new logit perturbation-based imbalance learning loss when proportion, variance, and distance imbalances exist simultaneously. Several classical losses become the special case of our proposed method. Meta learning is utilized to infer the hyper-parameters related to the three types of imbalance. Experimental results on several benchmark corpora validate the effectiveness of the proposed method.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 6 May 2023.

Builds on

30 of 48 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Wide Residual Networkscited by 3,070
  3. 2014Conditional Generative Adversarial Netscited by 2,162
  4. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  5. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  6. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  7. 2020Long-tail learning via logit adjustmentcited by 618
  8. 2021Deep Long-Tailed Learning: A Surveycited by 417
  9. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  10. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  11. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  12. 2021Delving into Deep Imbalanced Regressioncited by 158
18 more
  1. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  2. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  3. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
  4. 2019Imbalance Problems in Object Detection: A Reviewcited by 118
  5. 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
  6. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  7. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  8. 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 91
  9. 2022Balanced MSE for Imbalanced Visual Regressioncited by 89
  10. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  11. 2013Classification with Asymmetric Label Noise: Consistency and Maximal Denoisingcited by 68
  12. 2017Class Rectification Hard Mining for Imbalanced Deep Learningcited by 67
  13. 2016DisturbLabel: Regularizing CNN on the Loss Layercited by 41
  14. 2017Island Loss for Learning Discriminative Features in Facial Expression Recognitioncited by 35
  15. 2022Invariant Feature Learning for Generalized Long-Tailed Classificationcited by 34
  16. 2022The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regressioncited by 28
  17. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  18. 2021Tackling the Imbalance for GNNscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024Learning Equi-angular Representations for Online Continual Learningcited by 15
  2. 2023Data Optimization in Deep Learning: A Surveycited by 6
  3. 2024Validity of Feature Importance in Low-Performing Machine Learning for Tabular Biomedical Datacited by 0
  4. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0