Survey on deep learning with class imbalance

Justin Johnson; Taghi M. Khoshgoftaar

doi:https://doi.org/10.1186/s40537-019-0192-5

Survey on deep learning with class imbalance

2019 · Journal Of Big Data · 2,971 citations · 2 from inside this corpus

The purpose of this study is to examine existing deep learning techniques for addressing class imbalanced data. Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g., fraud detection and cancer detection. Moreover, highly imbalanced data poses added difficulty, as most learners will exhibit bias towards the majority class, and in extreme cases, may ignore the minority class altogether. Class imbalance has been studied thoroughly over the last two decades using traditional machine learning models, i.e. non-deep learning. Despite recent advances in deep learning, along with its increasing popularity, very little empirical work in the area of deep learning with class imbalance exists. Having achieved record-breaking performance results in several complex domains, investigating the use of deep neural networks for problems containing high levels of class imbalance is of great interest. Available studies regarding class imbalance and deep learning are surveyed in order to better understand the efficacy of deep learning when applied to class imbalanced data. This survey discusses the implementation details and experimental results for each study, and offers additional insight into their strengths and weaknesses. Several areas of focus include: data complexity, architectures tested, performance interpretation, ease of use, big data application, and generalization to other domains. We have found that research in this area is very limited, that most existing work focuses on computer vision tasks with convolutional neural networks, and that the effects of big data are rarely considered. Several traditional methods for class imbalance, e.g. data sampling and cost-sensitive learning, prove to be applicable in deep learning, while more advanced methods that exploit neural network feature learning abilities show promising results. The survey concludes with a discussion that highlights various gaps in deep learning from class imbalanced data for the purpose of guiding future research.

23 of 23 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

CatBoost for big data: an interdisciplinary review→Survey on deep learning with class imbalanceLegacy edge — source detail unavailable
Text Data Augmentation for Deep Learning→Survey on deep learning with class imbalanceLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Learning representations by back-propagating errorsLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Deep learning in neural networks: An overviewLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Advances in Neural Information Processing Systems 28Legacy edge — source detail unavailable
Survey on deep learning with class imbalance→Extreme learning machine: Theory and applicationsLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Automatic differentiation in PyTorchLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Learning from Imbalanced DataLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Deep LearningLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→The relationship between Precision-Recall and ROC curvesLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets LearningLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→A systematic study of the class imbalance problem in convolutional neural networksLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Deep learning applications and challenges in big data analyticsLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Exploratory Undersampling for Class-Imbalance LearningLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Learning from imbalanced data: open challenges and future directionsLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→EditorialLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→The foundations of cost-sensitive learningLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→KEEL: a software tool to assess evolutionary algorithms for data mining problemsLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Cost-sensitive boosting for classification of imbalanced dataLegacy edge — source detail unavailable
Survey on deep learning with class imbalance→Mining with rarityLegacy edge — source detail unavailable
SMOTEBoost: Improving Prediction of the Minority Class in Boosting→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Mining with rarity→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
Mining with rarity→The foundations of cost-sensitive learningLegacy edge — source detail unavailable
Mining with rarity→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Editorial→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
Editorial→The foundations of cost-sensitive learningLegacy edge — source detail unavailable
Editorial→Mining with rarityLegacy edge — source detail unavailable
Editorial→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Deep learning in neural networks: An overview→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
Cost-sensitive boosting for classification of imbalanced data→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
Cost-sensitive boosting for classification of imbalanced data→The foundations of cost-sensitive learningLegacy edge — source detail unavailable
Cost-sensitive boosting for classification of imbalanced data→Mining with rarityLegacy edge — source detail unavailable
Cost-sensitive boosting for classification of imbalanced data→EditorialLegacy edge — source detail unavailable
Cost-sensitive boosting for classification of imbalanced data→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Exploratory Undersampling for Class-Imbalance Learning→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
Exploratory Undersampling for Class-Imbalance Learning→The foundations of cost-sensitive learningLegacy edge — source detail unavailable
Exploratory Undersampling for Class-Imbalance Learning→Mining with rarityLegacy edge — source detail unavailable
Exploratory Undersampling for Class-Imbalance Learning→EditorialLegacy edge — source detail unavailable
Exploratory Undersampling for Class-Imbalance Learning→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Deep learning applications and challenges in big data analytics→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
Learning from Imbalanced Data→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
Learning from Imbalanced Data→The foundations of cost-sensitive learningLegacy edge — source detail unavailable
Learning from Imbalanced Data→Mining with rarityLegacy edge — source detail unavailable
Learning from Imbalanced Data→The relationship between Precision-Recall and ROC curvesLegacy edge — source detail unavailable
Learning from Imbalanced Data→EditorialLegacy edge — source detail unavailable
Learning from Imbalanced Data→Cost-sensitive boosting for classification of imbalanced dataLegacy edge — source detail unavailable
Learning from Imbalanced Data→Exploratory Undersampling for Class-Imbalance LearningLegacy edge — source detail unavailable
Learning from Imbalanced Data→Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets LearningLegacy edge — source detail unavailable
Learning from Imbalanced Data→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning→Mining with rarityLegacy edge — source detail unavailable
Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning→EditorialLegacy edge — source detail unavailable
Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
Learning from imbalanced data: open challenges and future directions→Learning from Imbalanced DataLegacy edge — source detail unavailable
Learning from imbalanced data: open challenges and future directions→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
A systematic study of the class imbalance problem in convolutional neural networks→SMOTEBoost: Improving Prediction of the Minority Class in BoostingLegacy edge — source detail unavailable
A systematic study of the class imbalance problem in convolutional neural networks→The foundations of cost-sensitive learningLegacy edge — source detail unavailable
A systematic study of the class imbalance problem in convolutional neural networks→Exploratory Undersampling for Class-Imbalance LearningLegacy edge — source detail unavailable
A systematic study of the class imbalance problem in convolutional neural networks→Learning from Imbalanced DataLegacy edge — source detail unavailable
A systematic study of the class imbalance problem in convolutional neural networks→Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets LearningLegacy edge — source detail unavailable
A systematic study of the class imbalance problem in convolutional neural networks→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
CatBoost for big data: an interdisciplinary review→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable
CatBoost for big data: an interdisciplinary review→Deep LearningLegacy edge — source detail unavailable
Text Data Augmentation for Deep Learning→SMOTE: Synthetic Minority Over-sampling TechniqueLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
SMOTE: Synthetic Minority Over-sampling Technique	2002	32,402
Learning representations by back-propagating errors	1986	31,688
Deep learning in neural networks: An overview	2014	18,236
A Fast Learning Algorithm for Deep Belief Nets	2006	16,540
Advances in Neural Information Processing Systems 28	2015	14,672
Extreme learning machine: Theory and applications	2006	13,310
Automatic differentiation in PyTorch	2017	11,099
Learning from Imbalanced Data	2009	10,209
Deep Learning	2016	8,952
The relationship between Precision-Recall and ROC curves	2006	6,427
Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning	2005	4,049
A systematic study of the class imbalance problem in convolutional neural networks	2018	3,072
Deep learning applications and challenges in big data analytics	2015	2,610
Exploratory Undersampling for Class-Imbalance Learning	2008	2,504
Learning from imbalanced data: open challenges and future directions	2016	2,489
Editorial	2004	2,081
The foundations of cost-sensitive learning	2001	1,837
SMOTEBoost: Improving Prediction of the Minority Class in Boosting	2003	1,680
KEEL: a software tool to assess evolutionary algorithms for data mining problems	2008	1,508
Cost-sensitive boosting for classification of imbalanced data	2007	1,438
Mining with rarity	2004	1,396

What cites it, inside the corpus

Paper	Year	Cited
CatBoost for big data: an interdisciplinary review	2020	1,776
Text Data Augmentation for Deep Learning	2021	1,701

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Imbalanced Data Classification Techniques	Computer Science
Electricity Theft Detection Techniques	Engineering
Vehicle License Plate Recognition	Engineering

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports2 author record(s) attached.
supports123 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:48+00:00.

sha256 46f669157f96ea35…