mlsanityData to 7 Oct 2026

A Comprehensive Survey on Imbalanced Data Learning

arXiv 2502.08960 ↗First posted 13 Feb 2025cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

With the expansion of data availability, machine learning (ML) has achieved remarkable breakthroughs in both academia and industry. However, imbalanced data distributions are prevalent in various types of raw data and severely hinder the performance of ML by biasing the decision-making processes. To deepen the understanding of imbalanced data and facilitate the related research and applications, this survey systematically analyzes various real-world data formats and concludes existing researches for different data formats into four distinct categories: data re-balancing, feature representation, training strategy, and ensemble learning. This structured analysis helps researchers comprehensively understand the pervasive nature of imbalance across diverse data formats, thereby paving a clearer path toward achieving specific research goals. We provide an overview of relevant open-source libraries, spotlight current challenges, and offer novel insights aimed at fostering future advancements in this critical area of study.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 136 of its 288 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

136 of 288 references.

References · 136

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2020Supervised Contrastive Learningcited by 2,803
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2014Conditional Generative Adversarial Netscited by 2,152
  11. 2020Knowledge Distillation: A Surveycited by 1,578
  12. 2019Contrastive Multiview Codingcited by 1,297
38 more
  1. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  2. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  3. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  4. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  5. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  6. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  7. 2020Long-tail learning via logit adjustmentcited by 605
  8. 2021Deep Long-Tailed Learning: A Surveycited by 416
  9. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  10. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  11. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  12. 2017Wasserstein Auto-Encoderscited by 371
  13. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  14. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 301
  15. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  16. 2021Parametric Contrastive Learningcited by 217
  17. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  18. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  19. 2016Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learningcited by 193
  20. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  21. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  22. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  23. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  24. 2021Delving into Deep Imbalanced Regressioncited by 157
  25. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  26. 2020Remix: Rebalanced Mixupcited by 144
  27. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 143
  28. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  29. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  30. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  31. 2022Semantic Image Synthesis via Diffusion Modelscited by 131
  32. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  33. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  34. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 122
  35. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  36. 2019Imbalance Problems in Object Detection: A Reviewcited by 118
  37. 2018Gradient Harmonized Single-stage Detectorcited by 114
  38. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111

50 most cited of 136 All 136 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 2026100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Modelscited by 3
  2. 2025Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methodscited by 1
  3. 2025Beyond Rebalancing: Benchmarking Binary Classifiers Under Class Imbalance Without Rebalancing Techniquescited by 0
  4. 2025Uncertainty-Aware Generative Oversampling Using an Entropy-Guided Conditional Variational Autoencodercited by 0
  5. 2026DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectorscited by 0
  6. 2026Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergencecited by 0
  7. 2026DADIR: Density-Aware Data-level Imbalanced Regression Frameworkcited by 0
  8. 2026Ensemble of Unsupervised Deep Learning for Clustering Imbalanced Tabular Datacited by 0
  9. 2026Rethinking Class Imbalance for Single-Cell Foundation Models: A Systematic Benchmark Across Architectures and Long-Tail Loss Functionscited by 0
  10. 2026Probabilistic Modelling of Operational Design Domains, A New Approach for Testing AI Systemscited by 0